Search

Recommendation systems are widely used in e-commerce websites and online platforms to address information overload. However, existing systems primarily rely on historical data and user feedback, making it difficult to capture user intent transitions. Recently, Knowledge Base (KB)-based models are proposed to incorporate expert knowledge, but it struggle to adapt to new items and the evolving e-commerce environment. To address these challenges, we propose a novel Large Language Model based Complementary Knowledge Enhanced Recommendation System (LLM-KERec). It introduces an entity extractor that extracts unified concept terms from item and user information. To provide cost-effective and reliable prior knowledge, entity pairs are generated based on entity popularity and specific strategies. The large language model determines complementary relationships in each entity pair, constructing a complementary knowledge graph. Furthermore, a new complementary recall module and an Entity-Entity-Item (E-E-I) weight decision model refine the scoring of the ranking model using real complementary exposure-click samples. Extensive experiments conducted on three industry datasets demonstrate the significant performance improvement of our model compared to existing approaches. Additionally, detailed analysis shows that LLM-KERec enhances users' enthusiasm for consumption by recommending complementary items. In summary, LLM-KERec addresses the limitations of traditional recommendation systems by incorporating complementary knowledge and utilizing a large language model to capture user intent transitions, adapt to new items, and enhance recommendation efficiency in the evolving e-commerce landscape., Comment: 9 pages, 5 figures

Length generalization failure problem, namely the large language model (LLM) fails to generalize to texts longer than its maximum training length, greatly restricts the application of LLM in the scenarios with streaming long inputs. To address this problem, the existing methods either require substantial costs or introduce precision loss. In this paper, we empirically find that the accuracy of the LLM's prediction is highly correlated to its certainty. Based on this, we propose an efficient training free framework, named XL3M (it means extra-long large language model), which enables the LLMs trained on short sequences to reason extremely long sequence without any further training or fine-tuning. Under the XL3M framework, the input context will be firstly decomposed into multiple short sub-contexts, where each sub-context contains an independent segment and a common ``question'' which is a few tokens from the end of the original context. Then XL3M gives a method to measure the relevance between each segment and the ``question'', and constructs a concise key context by splicing all the relevant segments in chronological order. The key context is further used instead of the original context to complete the inference task. Evaluations on comprehensive benchmarks show the superiority of XL3M. Using our framework, a Llama2-7B model is able to reason 20M long sequences on an 8-card Huawei Ascend 910B NPU machine with 64GB memory per card., Comment: 11 pages, 5 figures

Maximum distance separable (MDS) codes facilitate the achievement of elevated levels of fault tolerance in storage systems while incurring minimal redundancy overhead. Reed-Solomon (RS) codes are typical MDS codes with the sub-packetization level being one, however, they require large repair bandwidth defined as the total amount of symbols downloaded from other surviving nodes during single-node failure/repair. In this paper, we present the {\em set transformation}, which can transform any MDS code into set transformed code such that (i) the sub-packetization level is flexible and ranges from 2 to $(n-k)^{\lfloor\frac{n}{n-k}\rfloor}$ in which $n$ is the number of nodes and $k$ is the number of data nodes, (ii) the new code is MDS code, (iii) the new code has lower repair bandwidth for any single-node failure. We show that our set transformed codes have both lower repair bandwidth and lower field size than the existing related MDS array codes, such as elastic transformed codes \cite{10228984}. Specifically, our set transformed codes have $2\%-6.6\%$ repair bandwidth reduction compared with elastic transformed codes \cite{10228984} for the evaluated typical parameters.

The reduction of carbon dioxide using electrochemical cells is an appealing technology to store renewable electricity in a chemical form. The preferential adsorption of oxygen over carbon atoms of intermediates could improve the methanol selectivity due to the retention of C-O bond. However, the adsorbent-surface interaction is mainly related to the d states of transition metals in catalysts, thus it is difficult to promote the formation of oxygen-bound intermediates without affecting the carbon affinity. This paper describes the construction of a molybdenum-based metal carbide catalyst that promotes the formation and adsorption of oxygen-bound intermediates, where the sp states in catalyst are enabled to participate in the bonding of intermediates. A high Faradaic efficiency of 80.4% for methanol is achieved at -1.1 V vs. the standard hydrogen electrode.

The grain boundaries (GBs) in copper (Cu) electrocatalysts have been suggested as active sites for CO2 electroreduction to ethanol. Nevertheless, the mechanisms are still elusive. Herein, we describe how GBs tune the activity and selectivity for ethanol on two representative Cu-GB models, namely Cu∑3/(111) GB and Cu∑5/(100) GB, using joint first-principles calculations and experiments. The unique geometric structures on the GBs facilitate the adsorption of bidentate intermediates, *COOH and *CHO, which are crucial for CO2 activation and CO protonation. The decreased CO-CHO coupling barriers on the GBs can be rationalized via kinetics analysis. Furthermore, when introducing GBs into Cu (100), the product is selectively switched from ethylene to ethanol, due to the stabilization effect for *CH3CHO and inapposite geometric structure for *O adsorption, which are validated by experimental trends. An overall 12.5 A current and a single-pass conversion of 5.18% for ethanol can be achieved over the synthesized Cu-GB catalyst by scaling up the electrode into a 25 cm2 membrane electrode assembly system.

Heterogeneous catalysts, especially metal oxides, play a curial role in improving energy conversion efficiency and production of valuable chemicals. However, the surface structure at the atomic level and the nature of active sites are still ambiguous due to the dynamism of surface structure and difficulty in structure characterization under electrochemical conditions. This paper describes a strategy of the multiscale simulation to investigate the SnO x reduction process and to build a structure-performance relation of SnO x for CO2 electroreduction. Employing high-dimensional neural network potential accelerated molecular dynamics and stochastic surface walking global optimization, coupled with density functional theory calculations, we propose that SnO2 reduction is accompanied by surface reconstruction and charge density redistribution of active sites. A regulatory factor, the net charge, is identified to predict the adsorption capability for key intermediates on active sites. Systematic electronic analyses reveal the origin of the interaction between the adsorbates and the active sites. These findings uncover the quantitative correlation between electronic structure properties and the catalytic performance of SnO x so that Sn sites with moderate charge could achieve the optimally catalytic performance of the CO2 electroreduction to formate.

The complex reconstructed structure of materials can be revealed by global optimization. This paper describes a hybrid evolutionary algorithm (HEA) that combines differential evolution and genetic algorithms with a multi-tribe framework. An on-the-fly machine learning calculator is adopted to expedite the identification of low-lying structures. With a superior performance to other well-established methods, we further demonstrate its efficacy by optimizing the complex oxidized surface of Pt/Pd/Cu with different facets under (4 × 4) periodicity. The obtained structures are consistent with experimental results and are energetically lower than the previously presented model.

This paper proposes a super-resolution harmonic retrieval method for uncorrelated strictly non-circular signals, whose covariance and pseudo-covariance present Toeplitz and Hankel structures, respectively. Accordingly, the augmented covariance matrix constructed by the covariance and pseudo-covariance matrices is not only low rank but also jointly Toeplitz-Hankel structured. To efficiently exploit such a desired structure for high estimation accuracy, we develop a low-rank Toeplitz-Hankel covariance reconstruction (LRTHCR) solution employed over the augmented covariance matrix. Further, we design a fitting error constraint to flexibly implement the LRTHCR algorithm without knowing the noise statistics. In addition, performance analysis is provided for the proposed LRTHCR in practical settings. Simulation results reveal that the LRTHCR outperforms the benchmark methods in terms of lower estimation errors., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Signal Processing Systems

The recently proposed learned indexes have attracted much attention as they can adapt to the actual data and query distributions to attain better search efficiency. Based on this technique, several existing works build up indexes for multi-dimensional data and achieve improved query performance. A common paradigm of these works is to (i) map multi-dimensional data points to a one-dimensional space using a fixed space-filling curve (SFC) or its variant and (ii) then apply the learned indexing techniques. We notice that the first step typically uses a fixed SFC method, such as row-major order and z-order. It definitely limits the potential of learned multi-dimensional indexes to adapt variable data distributions via different query workloads. In this paper, we propose a novel idea of learning a space-filling curve that is carefully designed and actively optimized for efficient query processing. We also identify innovative offline and online optimization opportunities common to SFC-based learned indexes and offer optimal and/or heuristic solutions. Experimental results demonstrate that our proposed method, LMSFC, outperforms state-of-the-art non-learned or learned methods across three commonly used real-world datasets and diverse experimental settings.

Recently, learned heuristics have been widely applied to solve combinatorial optimization problems (e.g., traveling salesman problem (TSP)). However, the scalability of these learning-based methods hinders the applications in practical scenarios. Specifically, models pre-trained on the small-scale data generalize poorly to large-scale problems. Moreover, learning the heuristics directly for large-scale problems costs tremendous time and space. To extend the scalability of learned heuristics on TSP, we propose a Hierarchical neural framework for solving large-scale traveling salesman problems (HiTSPs) based on a divide-and-conquer strategy. In particular, the HiTSP framework first divides the large-scale problem into small-scale subproblems by node clustering. Each subproblem is conquered by a modified pointer network learned from reinforcement learning. The tour of the original TSP is constructed by linking solutions of subproblems and optimized by a novel segmented local search algorithm. Notably, the segmented local search algorithm leverages the node clustering information to prune many unnecessary operations and significantly reduces the complexity in theory. Extensive experiments show that HiTSP outperforms state-of-the-art learning-based methods and Google OR-Tools in large-scale cases. Moreover, compared to the best heuristic algorithms, HiTSP has a significant advantage in efficiency for large-scale TSP problems. © 2023, Operations Research Society of China, Periodicals Agency of Shanghai University, Science Press, and Springer-Verlag GmbH Germany, part of Springer Nature.

Many network applications can be formulated as NP-hard combinatorial optimization problems of community detection (CD) that partitions nodes of a graph into several groups with dense linkage. Most existing CD methods are transductive, which independently optimized their models for each single graph, and can only ensure either high quality or efficiency of CD by respectively using advanced machine learning techniques or fast heuristic approximation. In this study, we consider the CD task and aims to alleviate its NP-hard challenge. Motivated by the efficient inductive inference of graph neural networks (GNNs), we explore the possibility to achieve a better tradeoff between the quality and efficiency of CD via an inductive embedding scheme across multiple graphs of a system and propose a novel inductive community detection (ICD) method. Concretely, ICD first conducts the offline training of an adversarial dual GNN structure on historical graphs to capture key properties of a system. The trained model is then directly generalized to new graphs of the same system for online CD without additional optimization, where a better tradeoff between quality and efficiency can be achieved. Compared with existing inductive approaches, we develop a novel feature extraction module based on graph coarsening, which can efficiently extract informative feature inputs for GNNs. Moreover, our original designs of adversarial dual GNN and clustering regularization loss further enable ICD to capture permutation-invariant community labels in the offline training and help derive community-preserved embedding to support the high-quality online CD. Experiments on a set of benchmarks demonstrate that ICD can achieve a significant tradeoff between quality and efficiency over various baselines.

Abundant high-rate (n, k) minimum storage regenerating (MSR) codes have been reported in the literature. However, most of them require contacting all the surviving nodes during a node repair process, resulting in a repair degree of d=n-1. In practical systems, it may not always be feasible to connect and download data from all surviving nodes, as some nodes may be unavailable. Therefore, there is a need for MSR code constructions with a repair degree of dk, and has a smaller sub-packetization level or finite field than some existing constructions. Additionally, in conjunction with a previous generic transformation to reduce the sub-packetization level, we obtain an MDS array code with a small sub-packetization level and $(1+\epsilon)$-optimal repair bandwidth (i.e., $(1+\epsilon)$ times the optimal repair bandwidth) for repair degree d=n-1. This code outperforms some existing ones in terms of either the sub-packetization level or the field size., Comment: Submitted to the IEEE Transactions on Communications

Temporal link prediction (TLP) is an inference task on dynamic graphs that predicts future topology using historical graph snapshots. Existing TLP methods are usually designed for unweighted graphs with fixed node sets. Some of them cannot be generalized to the prediction of weighted graphs with non-fixed node sets. Although several methods can still be used to predict weighted graphs, they can only derive low-quality prediction snapshots sensitive to large edge weights but fail to distinguish small and zero weights in adjacency matrices. In this study, we consider the challenging high-quality TLP on weighted dynamic graphs and propose a novel inductive dynamic embedding aggregation (IDEA) method, inspired by the high-resolution video prediction. IDEA combines conventional error minimization objectives with a scale difference minimization objective, which can generate high-quality weighted prediction snapshots, distinguishing differences among large, small, and zero weights in adjacency matrices. Since IDEA adopts an inductive dynamic embedding scheme with an attentive node aligning unit and adaptive embedding aggregation module, it can also tackle the TLP on weighted graphs even with non-fixed node sets. Experiments on datasets of various scenarios validate that IDEA can derive high-quality prediction results for weighted dynamic graphs and tackle the variation of node sets. IEEE

Federated learning allows edge devices to collaboratively train a global model without sharing their local private data. Yet, with limited network bandwidth at the edge, communication often becomes a severe bottleneck. In this paper, we find that it is unnecessary to always synchronize the full model in the entire training process, because many parameters already become mature (i.e., stable) prior to model convergence, and can thus be excluded from later synchronizations. This allows us to reduce the communication overhead without compromising the model accuracy. However, challenges are that the local parameters excluded from global synchronization may diverge on different clients, and meanwhile some parameters may stabilize only temporally. To address these challenges, we propose a novel scheme called Adaptive Parameter Freezing (APF), which fixes (freezes) the non-synchronized stable parameters in intermittent periods. Specifically, the freezing periods are tentatively adjusted in an additively-increase and multiplicatively-decrease manner—depending on whether the previously-frozen parameters remain stable in subsequent iterations. We also extend APF into APF# and APF++, which freeze parameters in a more aggressive manner to achieve larger performance benefit for large complex models. We implemented APF and its variants as Python modules with PyTorch, and extensive experiments show that APF can reduce data transfer amount by over 60%. IEEE

Federated learning (FL) enables distributed clients to collectively train a global model without revealing their private data, and for efficiency clients synchronize their gradients periodically. However, this can lead to the inaccuracy in model convergence due to inconsistent data distributions among clients. In this work, we find that there is a strong correlation between FL accuracy loss and the synchronization frequency, and seek to fine tune the synchronization frequency at training runtime to make FL accurate and also efficient. Specifically, aware that under the FL privacy requirement only gradients can be utilized for making frequency tuning decisions, we propose a novel metric called gradient consistency, which can effectively reflect the training status despite the instability of realistic FL scenarios. We further devise a feedback-driven algorithm called Gradient-Instructed Frequency Tuning (GIFT), which adaptively increases or decreases the synchronization frequency based on the gradient consistency metric. We have implemented GIFT in PyTorch, and large-scale evaluations show that it can improve FL accuracy by up to 10.7% with a time reduction of 58.1%.

A popular branch of stochastic network calculus (SNC) utilizes moment-generating functions (MGFs) to characterize arrivals and services, which enables end-to-end performance analysis. However, existing traffic models for SNC cannot effectively represent the complicated nature of real-world network traffic such as dramatic burstiness. To conquer this challenge, we propose an adaptive spatial-temporal traffic model: dMAPAR-HMM. Specifically, we model the temporal on-off switching process as a dual Markovian arrival process (dMAP) and the arrivals during the on phases as an autoregressive hidden Markov model (AR-HMM). The dMAPAR-HMM model fits in with the MGF-SNC analysis framework, unifies various state-of-the-art arrival models, and matches real-world data more closely. We perform extensive experiments with real-world traces under different network topologies and utilization levels. Experimental results show that dMAPAR-HMM significantly outperforms prevailing models in MGF-SNC.

The recently proposed learned indexes have attracted much attention as they can adapt to the actual data and query distributions to attain better search efficiency. Based on this technique, several existing works build up indexes for multi-dimensional data and achieve improved query performance. A common paradigm of these works is to (i) map multi-dimensional data points to a one-dimensional space using a fixed space-filling curve (SFC) or its variant and (ii) then apply the learned indexing techniques. We notice that the first step typically uses a fixed SFC method, such as row-major order and z-order. It definitely limits the potential of learned multi-dimensional indexes to adapt variable data distributions via different query workloads. In this paper, we propose a novel idea of learning a space-filling curve that is carefully designed and actively optimized for efficient query processing. We also identify innovative offline and online optimization opportunities common to SFC-based learned indexes and offer optimal and/or heuristic solutions. Experimental results demonstrate that our proposed method, LMSFC, outperforms state-of-the-art non-learned or learned methods across three commonly used real-world datasets and diverse experimental settings., Comment: Extended Version. Accepted by VLDB 2023

Maximum distance separable (MDS) codes have the optimal trade-off between storage efficiency and fault tolerance, which are widely used in distributed storage systems. As typical non-MDS codes, simple regenerating codes (SRCs) can achieve both smaller repair bandwidth and smaller repair locality than traditional MDS codes in repairing single-node erasure. In this paper, we propose {\em generalized simple regenerating codes} (GSRCs) that can support much more parameters than that of SRCs. We show that there is a trade-off between sub-packetization and fault tolerance in our GSRCs, and SRCs achieve a special point of the trade-off of GSRCs. We show that the fault tolerance of our GSRCs increases when the sub-packetization increases linearly. We also show that our GSRCs can locally repair any singe-symbol erasure and any single-node erasure, and the repair bandwidth of our GSRCs is smaller than that of the existing related codes.

High-rate minimum storage regenerating (MSR) codes are known to require a large sub-packetization level, which can make meta-data management difficult and hinder implementation in practical systems. A few maximum distance separable (MDS) array code constructions have been proposed to attain a much smaller sub-packetization level by sacrificing a bit of repair bandwidth. However, to the best of our knowledge, only one construction by Guruswami et al. can support the repair of a failed node without contacting all the surviving nodes. This construction is certainly of theoretical interest but not yet practical due to its requirement for very large code parameters. In this paper, we propose a generic transformation that can convert any $(\overline{n}, \overline{k})$ MSR code with a repair degree of $\overline{d}<\overline{n}-1$ into another $(n=s\overline{n},k)$ MDS array code that supports $d

This paper develops an efficient solution for super-resolution two-dimensional (2D) harmonic retrieval from multiple measurement vectors (MMV). Given the sample covariance matrix constructed from the MMV, a gridless compressed sensing approach is proposed based on the atomic norm minimization (ANM). In the approach, our key step is to perform a redundancy reduction (RR) transformation that effectively reduces the large problem size at hand, without loss of useful frequency information. For uncorrelated sources, the transformed 2D covariance matrices in the RR domain retain a salient structure, which permits a sparse representation over a matrix-form atom set with decoupled 1D frequency components. Accordingly, the decoupled ANM (D-ANM) framework can be applied for super-resolution 2D frequency estimation. Moreover, the resulting RR-enabled D-ANM technique, termed RR-D-ANM, further allows an efficient relaxation under certain conditions, which leads to low computational complexity of the same order as the 1D case. Simulation results verify the advantages of our solutions over benchmark methods, in terms of higher computational efficiency and detectability for 2D harmonic retrieval., taverne, Circuits and Systems

We study the $\bar B_s^0 \to J/\psi f_0(980)$ and $\bar B_s^0 \to J/\psi a_0(980)$ reactions, and pay attention to the different sources of isospin violation and mixing of $f_0(980)$ and $a_0(980)$ resonances where these resonances are dynamically generated from meson-meson interaction. We find that the main reason of isospin violation is the isospin breaking in the meson-meson transition $T$ matrices, and the other source is that the loops involving kaons in the production mechanism provide a source of isospin violation because they do not cancel by the different mass of the charged and neutral kaons. We obtain a branching ratio for $a_0(980)$ production of the order of $5 \times 10^{-6}$. Future experiments can address this problem and the production rate and shape of the $\pi^0 \eta$ mass distribution will definitely help to better understand the nature of scalar resonances., Comment: 12 pages, 4 figures

Directional migration initiated at the wound edge leads epithelia to migrate in wound healing. How such coherent migration is achieved is not well understood. Here, we used electric fields to induce robust migration of sheets of human keratinocytes and developed an in silico model to characterize initiation and propagation of epithelial collective migration. Electric fields initiate an increase in migration directionality and speed at the leading edge. The increases propagate across the epithelial sheets, resulting in directional migration of cell sheets as coherent units. Both the experimental and in silico models demonstrated vector-like integration of the electric and default directional cues at free edge in space and time. The resultant collective migration is consistent in experiments and modeling, both qualitatively and quantitatively. The keratinocyte model thus faithfully reflects key features of epithelial migration as a coherent tissue in vivo, e.g. that leading cells lead, and that epithelium maintains cell-cell junction.

In the electrochemical CO2 reduction reaction (CO2RR), halide ions could impose a significant effect on multi-carbon (C2+) product production for Cu-based catalysts by a combined contribution from various mechanisms. However, the nature of specific adsorption of halide ions remains elusive due to the difficulty in decoupling different effects. This paper describes a facile method to actively immobilize the morphology of Cu-based catalysts during the CO2RR, which makes it possible to reveal the fundamental mechanism of specific adsorption of halide ions. A stable morphology is obtained by pre-reduction in aqueous KX (X = Cl, Br, I) electrolytes followed by conducting the CO2RR using non-buffered and non-specifically adsorbed K2SO4 as the supporting electrolyte, by which the change of local pH and cation concentration is also maintained during the CO2RR. In situ spectroscopy revealed that the specific adsorption of halide ions enhances the adsorption of *CO intermediates, which enables a high selectivity of 84.5% for C2+ products in 1.0 M KI.

Partial maximum distance separable (PMDS) codes are a kind of erasure codes where the nodes are divided into multiple groups with each forming an MDS code with a smaller code length, thus they allow repairing a failed node with only a few helper nodes and can correct all erasure patterns that are information-theoretically correctable. However, the repair of a failed node of PMDS codes still requires a large amount of communication if the group size is large. Recently, PMDS array codes with each local code being an MSR code were introduced to reduce the repair bandwidth further. However, they require extensive rebuilding access and unavoidably a significant sub packetization level. In this paper, we first propose two constructions of PMDS array codes with two global parities that have smaller sub-packetization levels and much smaller finite fields than the existing one. One construction can support an arbitrary number of local parities and has $(1+\epsilon)$-optimal repair bandwidth (i.e., $(1+\epsilon)$ times the optimal repair bandwidth), while the other one is limited to two local parities but has significantly smaller rebuilding access and its sub packetization level is only $2$. In addition, we present a construction of PMDS array code with three global parities, which has a smaller sub-packetization level as well as $(1+\epsilon)$-optimal repair bandwidth, the required finite field is significantly smaller than existing ones., Comment: Accepted for publication in the IEEE Transactions on Information Theory

Many network applications can be formulated as NP-hard combinatorial optimization problems of community detection (CD). Due to the NP-hardness, to balance the CD quality and efficiency remains a challenge. Most existing CD methods are transductive, which are independently optimized only for the CD on a single graph. Some of these methods use advanced machine learning techniques to obtain high-quality CD results but usually have high complexity. Other approaches use fast heuristic approximation to ensure low runtime but may suffer from quality degradation. In contrast to these transductive methods, we propose an alternative inductive community detection (ICD) method across graphs of a system or scenario to alleviate the NP-hard challenge. ICD first conducts the offline training of an adversarial dual GNN on historical graphs to capture key properties of the system. The trained model is then directly generalized to new unseen graphs for online CD without additional optimization, where a better trade-off between quality and efficiency can be achieved. ICD can also capture the permutation invariant community labels in the offline training and tackle the online CD on new graphs with non-fixed number of nodes and communities. Experiments on a set of benchmarks demonstrate that ICD can achieve a significant trade-off between quality and efficiency over various baselines.

The disentanglement of StyleGAN latent space has paved the way for realistic and controllable image editing, but does StyleGAN know anything about temporal motion, as it was only trained on static images? To study the motion features in the latent space of StyleGAN, in this paper, we hypothesize and demonstrate that a series of meaningful, natural, and versatile small, local movements (referred to as "micromotion", such as expression, head movement, and aging effect) can be represented in low-rank spaces extracted from the latent space of a conventionally pre-trained StyleGAN-v2 model for face generation, with the guidance of proper "anchors" in the form of either short text or video clips. Starting from one target face image, with the editing direction decoded from the low-rank space, its micromotion features can be represented as simple as an affine transformation over its latent feature. Perhaps more surprisingly, such micromotion subspace, even learned from just single target face, can be painlessly transferred to other unseen face images, even those from vastly different domains (such as oil painting, cartoon, and sculpture faces). It demonstrates that the local feature geometry corresponding to one type of micromotion is aligned across different face subjects, and hence that StyleGAN-v2 is indeed "secretly" aware of the subject-disentangled feature variations caused by that micromotion. We present various successful examples of applying our low-dimensional micromotion subspace technique to directly and effortlessly manipulate faces, showing high robustness, low computational overhead, and impressive domain transferability. Our codes are available at https://github.com/wuqiuche/micromotion-StyleGAN., Comment: 13 pages, 8 figures

On-boarding new devices into an existing SDN network is a pain for network operations (NetOps) teams, because much expert effort is required to bridge the gap between the configuration models of the new devices and the unified data model in the SDN controller. In this work, we present an assistant framework NAssim, to help NetOps accelerate the process of assimilating a new device into a SDN network. Our solution features a unified parser framework to parse diverse device user manuals into preliminary configuration models, a rigorous validator that confirm the correctness of the models via formal syntax analysis, model hierarchy validation and empirical data validation, and a deep-learning-based mapping algorithm that uses state-of-The-Art neural language processing techniques to produce human-comprehensible recommended mapping between the validated configuration model and the one in the SDN controller. In all, NAssim liberates the NetOps from most tedious tasks by learning directly from devices' manuals to produce data models which are comprehensible by both the SDN controller and human experts. Our evaluation shows, NAssim can accelerate the assimilation process by 9.1x. In this process, we also identify and correct 243 errors in four mainstream vendors' device manuals, and release a validated and expert-curated dataset of parsed manual corpus for future research. © 2022 ACM.

This paper proposes an efficient direction of departure (DOD) and direction of arrival (DOA) estimation method for multi-input multi-output (MIMO) systems. For uncorrelated scenarios, the redundancy of the covariance matrix is first exploited by establishing its concise representation through redundancy reduction, which transforms the original large-size covariance matrix into a smaller-size matrix without loss of useful angle information. Then, the resulting transformed matrix, which retains a salient structure, permits efficient two-dimensional (2D) angle estimators working on a reduced-size problem for DOD and DOA estimation. Compared with conventional subspace-based methods, the proposed method incorporating an appropriate 2D angle estimator is more computationally efficient and can achieve higher estimation accuracy for small numbers of snapshots and low signal-to-noise ratios, which are verified by simulation results., Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Signal Processing Systems

This paper develops an efficient solution for super-resolution two-dimensional (2D) harmonic retrieval from multiple measurement vectors (MMV). Given the sample covariance matrix constructed from the MMV, a gridless compressed sensing approach is proposed based on the atomic norm minimization (ANM). In the approach, our key step is to perform a redundancy reduction (RR) transformation that effectively reduces the large problem size at hand, without loss of useful frequency information. For uncorrelated sources, the transformed 2D covariance matrices in the RR domain retain a salient structure, which permits a sparse representation over a matrix-form atom set with decoupled 1D frequency components. Accordingly, the decoupled ANM (D-ANM) framework can be applied for super-resolution 2D frequency estimation. Moreover, the resulting RR-enabled D-ANM technique, termed RR-D-ANM, further allows an efficient relaxation under certain conditions, which leads to low computational complexity of the same order as the 1D case. Simulation results verify the advantages of our solutions over benchmark methods, in terms of higher computational efficiency and detectability for 2D harmonic retrieval., Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Signal Processing Systems

Contains fulltext : 234394.pdf (Publisher’s version ) (Open Access)

Data-driven approaches have recently emerged as promising remedies for communication system designs, which leverage deep learning techniques for automated development and optimization. In this paper, we revisit the designs of multi-input multi-output (MIMO) wireless systems and investigate the end-to-end learning for MIMO systems with temporal correlations. Our objective is to develop a MIMO transceiver to improve the communication performance by making fully use of the available temporal information. Although the end-to-end learning framework has been applied to various communication systems, existing designs largely rely on memoryless autoencoders (AEs) and overlook the time dependency. To overcome this issue, we propose a novel learning-based MIMO transceiver, namely, the TC-MIMONet, which extends the conventional memoryless AE-based transceivers by customizing two neural network components with memory. In particular, a long short-term memory (LSTM)-based CSI predictor is adopted at the transmitter, while a two-timescale LSTM-based decoder is developed for the receiver. Simulation results show that TC-MIMONet achieves significant block error rate reduction compared to two baseline schemes without utilizing the available temporal information. © 2021 IEEE.

Federated learning allows edge devices to collaboratively train a global model by synchronizing their local updates without sharing private data. Yet, with limited network bandwidth at the edge, communication often becomes a severe bottleneck. In this paper, we find that it is unnecessary to always synchronize the full model in the entire training process, because many parameters gradually stabilize prior to the ultimate model convergence, and can thus be excluded from being synchronized at an early stage. This allows us to reduce the communication overhead without compromising the model accuracy. However, challenges are that the local parameters excluded from global synchronization may diverge on different clients, and meanwhile some parameters may stabilize only temporally. To address these challenges, we propose a novel scheme called Adaptive Parameter Freezing (APF), which fixes (freezes) the non-synchronized stable parameters in intermittent periods. Specifically, the freezing periods are tentatively adjusted in an additively-increase and multiplicatively-decrease manner, depending on if the previously-frozen parameters remain stable in subsequent iterations. We implemented APF as a Python module in PyTorch. Our extensive array of experimental results show that APF can reduce data transfer by over 60%. © 2021 IEEE.

With the growing demand for high-speed data transmission, multiple-input multiple-output (MIMO) technology has been widely used in 5G wireless communication systems. Practically, analog-to-digital converters (ADCs) are employed to reduce the high power consumption problem caused by using a large number of antennas. However, one significant bottleneck restricting the performance of such MIMO systems is the infeasibility to jointly design the transceiver and the ADCs. To address this problem, this paper proposes an autoencoder solution driven by deep learning methods, for MIMO Rayleigh fading channels. Specifically, by viewing the entire MIMO system as an auto encoder, the encoding-decoding pair and the ADCs can be trained simultaneously and optimized in an end-to-end manner, which can also be easily adapted for different information transmission rates. Moreover, in order to enable the gradient passing for ADCs, a smooth function (i.e., arctan(.)) is used to finely approximate the quantization layers of original ADCs. Finally, simulation results reveal the improved performance on both accuracy and stability of the proposed autoencoder based framework in MIMO systems. © 2021 IEEE.

In this paper, we consider two rack-aware storage systems. First, large-scale rack-aware storage system, which is very common in large-scale storage system, is a rack-aware storage system where all sizes of racks are at least the number of redundant nodes. For such storage system, we prove that any Maximum Distance Separable (MDS) codes can have optimal inter-rack repair bandwidth and give a closed-form representation of all repair schemes with optimal inter-rack repair bandwidth. Furthermore, we show that the optimal repair access and optimal inter-rack repair bandwidth can be attained simultaneously for such storage system. Second, we investigate the rack-aware storage system of all racks with the same size, which is called uniform rack-aware storage system. We prove that, except the trivial cases, we cannot attain optimal inter-rack repair bandwidth and optimal repair access for such storage system at the same time. Specifically, we establish the lower bound of repair access for a repair scheme with optimal interrack repair bandwidth, which is tight for some parameters, and also the tight lower bound of inter-rack repair bandwidth for a repair scheme with optimal repair access. © 2021 IEEE.

Regenerating codes are designed to reduce the repair bandwidth (access bandwidth) for rebuilding a fail node in an erasure-coded storage system. In practical systems, the fail node is not rebuilt immediately. Before its rebuilding, the data originally stored in the failed node might be accessed by the system. Hence, accessing the data in the failed disk (degraded read) with low latency is crucial for any practical storage system. In this work, to solve this problem, a new class of the regenerating codes based on the maximum distance separable (MDS) array codes is defined, named the MDS array code with the property of degraded read friendly (DRF). For the DRF MDS array codes with 2 redundant nodes and the sub-packetization level of 2, the lower bound of their access bandwidth is derived. A class of the DRF MDS array codes that achieves the derived bound is given to solidify the achievability of the proposed lower bound. © 2021 IEEE.

Federated learning allows edge devices to collaboratively train a global model by synchronizing their local updates without sharing private data. Yet, with limited network bandwidth at the edge, communication often becomes a severe bottleneck. In this paper, we find that it is unnecessary to always synchronize the full model in the entire training process, because many parameters gradually stabilize prior to the ultimate model convergence, and can thus be excluded from being synchronized at an early stage. This allows us to reduce the communication overhead without compromising the model accuracy. However, challenges are that the local parameters excluded from global synchronization may diverge on different clients, and meanwhile some parameters may stabilize only temporally. To address these challenges, we propose a novel scheme called Adaptive Parameter Freezing (APF), which fixes (freezes) the non-synchronized stable parameters in intermittent periods. Specifically, the freezing periods are tentatively adjusted in an additively-increase and multiplicatively-decrease manner, depending on if the previously-frozen parameters remain stable in subsequent iterations. We implemented APF as a Python module in PyTorch. Our extensive array of experimental results show that APF can reduce data transfer by over 60%. © 2021 IEEE.

Data-driven approaches have recently emerged as promising remedies for communication system designs, which leverage deep learning techniques for automated development and optimization. In this paper, we revisit the designs of multi-input multi-output (MIMO) wireless systems and investigate the end-to-end learning for MIMO systems with temporal correlations. Our objective is to develop a MIMO transceiver to improve the communication performance by making fully use of the available temporal information. Although the end-to-end learning framework has been applied to various communication systems, existing designs largely rely on memoryless autoencoders (AEs) and overlook the time dependency. To overcome this issue, we propose a novel learning-based MIMO transceiver, namely, the TC-MIMONet, which extends the conventional memoryless AE-based transceivers by customizing two neural network components with memory. In particular, a long short-term memory (LSTM)-based CSI predictor is adopted at the transmitter, while a two-timescale LSTM-based decoder is developed for the receiver. Simulation results show that TC-MIMONet achieves significant block error rate reduction compared to two baseline schemes without utilizing the available temporal information. © 2021 IEEE.

Contains fulltext : 234394.pdf (Publisher’s version ) (Open Access)

Contains fulltext : 234394.pdf (Publisher’s version ) (Open Access)

Controllable image synthesis models allow creation of diverse images based on text instructions or guidance from a reference image. Recently, denoising diffusion probabilistic models have been shown to generate more realistic imagery than prior methods, and have been successfully demonstrated in unconditional and class-conditional settings. We investigate fine-grained, continuous control of this model class, and introduce a novel unified framework for semantic diffusion guidance, which allows either language or image guidance, or both. Guidance is injected into a pretrained unconditional diffusion model using the gradient of image-text or image matching scores, without re-training the diffusion model. We explore CLIP-based language guidance as well as both content and style-based image guidance in a unified framework. Our text-guided synthesis approach can be applied to datasets without associated text annotations. We conduct experiments on FFHQ and LSUN datasets, and show results on fine-grained text-guided image synthesis, synthesis of images related to a style or content reference image, and examples with both textual and image guidance., Comment: WACV 2023. Project page https://xh-liu.github.io/sdg

With the rapid expansion of graphs and networks and the growing magnitude of data from all areas of science, effective treatment and compression schemes of context-dependent data is extremely desirable. A particularly interesting direction is to compress the data while keeping the "structural information" only and ignoring the concrete labelings. Under this direction, Choi and Szpankowski introduced the structures (unlabeled graphs) which allowed them to compute the structural entropy of the Erd\H{o}s--R\'enyi random graph model. Moreover, they also provided an asymptotically optimal compression algorithm that (asymptotically) achieves this entropy limit and runs in expectation in linear time. In this paper, we consider the Stochastic Block Models with an arbitrary number of parts. Indeed, we define a partitioned structural entropy for Stochastic Block Models, which generalizes the structural entropy for unlabeled graphs and encodes the partition information as well. We then compute the partitioned structural entropy of the Stochastic Block Models, and provide a compression scheme that asymptotically achieves this entropy limit.

Accurate organ at risk (OAR) segmentation is critical to reduce the radiotherapy post-treatment complications. Consensus guidelines recommend a set of more than 40 OARs in the head and neck (H&N) region, however, due to the predictable prohibitive labor-cost of this task, most institutions choose a substantially simplified protocol by delineating a smaller subset of OARs and neglecting the dose distributions associated with other OARs. In this work we propose a novel, automated and highly effective stratified OAR segmentation (SOARS) system using deep learning to precisely delineate a comprehensive set of 42 H&N OARs. SOARS stratifies 42 OARs into anchor, mid-level, and small & hard subcategories, with specifically derived neural network architectures for each category by neural architecture search (NAS) principles. We built SOARS models using 176 training patients in an internal institution and independently evaluated on 1327 external patients across six different institutions. It consistently outperformed other state-of-the-art methods by at least 3-5% in Dice score for each institutional evaluation (up to 36% relative error reduction in other metrics). More importantly, extensive multi-user studies evidently demonstrated that 98% of the SOARS predictions need only very minor or no revisions for direct clinical acceptance (saving 90% radiation oncologists workload), and their segmentation and dosimetric accuracy are within or smaller than the inter-user variation. These findings confirmed the strong clinical applicability of SOARS for the OAR delineation process in H&N cancer radiotherapy workflows, with improved efficiency, comprehensiveness, and quality.

Regenerating codes are designed to reduce the repair bandwidth (access bandwidth) for rebuilding a fail node in an erasure-coded storage system. In practical systems, the fail node is not rebuilt immediately. Before its rebuilding, the data originally stored in the failed node might be accessed by the system. Hence, accessing the data in the failed disk (degraded read) with low latency is crucial for any practical storage system. In this work, to solve this problem, a new class of the regenerating codes based on the maximum distance separable (MDS) array codes is defined, named the MDS array code with the property of degraded read friendly (DRF). For the DRF MDS array codes with 2 redundant nodes and the sub-packetization level of 2, the lower bound of their access bandwidth is derived. A class of the DRF MDS array codes that achieves the derived bound is given to solidify the achievability of the proposed lower bound. © 2021 IEEE.

In this paper, we consider two rack-aware storage systems. First, large-scale rack-aware storage system, which is very common in large-scale storage system, is a rack-aware storage system where all sizes of racks are at least the number of redundant nodes. For such storage system, we prove that any Maximum Distance Separable (MDS) codes can have optimal inter-rack repair bandwidth and give a closed-form representation of all repair schemes with optimal inter-rack repair bandwidth. Furthermore, we show that the optimal repair access and optimal inter-rack repair bandwidth can be attained simultaneously for such storage system. Second, we investigate the rack-aware storage system of all racks with the same size, which is called uniform rack-aware storage system. We prove that, except the trivial cases, we cannot attain optimal inter-rack repair bandwidth and optimal repair access for such storage system at the same time. Specifically, we establish the lower bound of repair access for a repair scheme with optimal interrack repair bandwidth, which is tight for some parameters, and also the tight lower bound of inter-rack repair bandwidth for a repair scheme with optimal repair access. © 2021 IEEE.

Data-driven approaches have recently emerged as promising remedies for communication system designs, which leverage deep learning techniques for automated development and optimization. In this paper, we revisit the designs of multi-input multi-output (MIMO) wireless systems and investigate the end-to-end learning for MIMO systems with temporal correlations. Our objective is to develop a MIMO transceiver to improve the communication performance by making fully use of the available temporal information. Although the end-to-end learning framework has been applied to various communication systems, existing designs largely rely on memoryless autoencoders (AEs) and overlook the time dependency. To overcome this issue, we propose a novel learning-based MIMO transceiver, namely, the TC-MIMONet, which extends the conventional memoryless AE-based transceivers by customizing two neural network components with memory. In particular, a long short-term memory (LSTM)-based CSI predictor is adopted at the transmitter, while a two-timescale LSTM-based decoder is developed for the receiver. Simulation results show that TC-MIMONet achieves significant block error rate reduction compared to two baseline schemes without utilizing the available temporal information. © 2021 IEEE.

Federated learning allows edge devices to collaboratively train a global model by synchronizing their local updates without sharing private data. Yet, with limited network bandwidth at the edge, communication often becomes a severe bottleneck. In this paper, we find that it is unnecessary to always synchronize the full model in the entire training process, because many parameters gradually stabilize prior to the ultimate model convergence, and can thus be excluded from being synchronized at an early stage. This allows us to reduce the communication overhead without compromising the model accuracy. However, challenges are that the local parameters excluded from global synchronization may diverge on different clients, and meanwhile some parameters may stabilize only temporally. To address these challenges, we propose a novel scheme called Adaptive Parameter Freezing (APF), which fixes (freezes) the non-synchronized stable parameters in intermittent periods. Specifically, the freezing periods are tentatively adjusted in an additively-increase and multiplicatively-decrease manner, depending on if the previously-frozen parameters remain stable in subsequent iterations. We implemented APF as a Python module in PyTorch. Our extensive array of experimental results show that APF can reduce data transfer by over 60%. © 2021 IEEE.

With the growing demand for high-speed data transmission, multiple-input multiple-output (MIMO) technology has been widely used in 5G wireless communication systems. Practically, analog-to-digital converters (ADCs) are employed to reduce the high power consumption problem caused by using a large number of antennas. However, one significant bottleneck restricting the performance of such MIMO systems is the infeasibility to jointly design the transceiver and the ADCs. To address this problem, this paper proposes an autoencoder solution driven by deep learning methods, for MIMO Rayleigh fading channels. Specifically, by viewing the entire MIMO system as an auto encoder, the encoding-decoding pair and the ADCs can be trained simultaneously and optimized in an end-to-end manner, which can also be easily adapted for different information transmission rates. Moreover, in order to enable the gradient passing for ADCs, a smooth function (i.e., arctan(.)) is used to finely approximate the quantization layers of original ADCs. Finally, simulation results reveal the improved performance on both accuracy and stability of the proposed autoencoder based framework in MIMO systems. © 2021 IEEE.

Cross-lingual entity alignment, which aims to precisely connect the same entities in different monolingual knowledge bases (KBs) together, often suffers challenges from feature inconsistency to sequence context unawareness. This paper presents a dual adversarial learning framework for cross-lingual entity alignment, DAEA, with two original contributions. First, in order to address the structural and attribute feature inconsistency between entities in two knowledge graphs (KGs), an adversarial kernel embedding technique is proposed to extract graph-invariant information in an unsupervised manner, and project two KGs into the common embedding space. Second, in order to further improve successful rate of entity alignment, we propose to produce multiple random walks through each entity to be aligned and mask these entities in random walks. With the guidance of known aligned entities in the context of multiple random walks, an adversarial knowledge translation model is developed to fill and translate masked entities in pairwise random walks from two KGs. Extensive experiments performed on real-world datasets show that DAEA can well solve the feature inconsistency and sequence context unawareness issues and significantly outperforms thirteen state-of-the-art entity alignment methods.

Accessing the data in the failed disk (degraded read) with low latency is crucial for an erasure-coded storage system. In this work, the maximum distance separable (MDS) array code with the property of degraded-read friendly (DRF) is discussed. For the DRF MDS array code with 2 redundant nodes and the sub-packetization level of 2, the lower bound of its access bandwidth is derived., Comment: 22 pages, 1 figure

This paper develops an enhanced low-rank structured covariance reconstruction (LRSCR) method based on the decoupled atomic norm minimization (D-ANM), for super-resolution two-dimensional (2D) harmonic retrieval with multiple measurement vectors. This LRSCR-D-ANM approach exploits a potential structure hidden in the covariance by transferring the basic LRSCR to an efficient D-ANM formulation, which permits a sparse representation over a matrix-form atom set with decoupled 1D frequency components. The new LRSCR-D-ANM method builds upon the existence of a generalized Vandermonde decomposition of its solution, which otherwise cannot be guaranteed by the basic LRSCR unless a very conservative condition holds. Further, a low-complexity solution of the LRSCR-D-ANM is provided for fast implementation with negligible performance loss. Simulation results verify the advantages of the proposed LRSCR-D-ANM over the basic LRSCR, in terms of the wider applicability and the lower complexity., Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Circuits and Systems