Search

Graph representation learning is fundamental for analyzing graph-structured data. Exploring invariant graph representations remains a challenge for most existing graph representation learning methods. In this paper, we propose a cross-view graph consistency learning (CGCL) method that learns invariant graph representations for link prediction. First, two complementary augmented views are derived from an incomplete graph structure through a bidirectional graph structure augmentation scheme. This augmentation scheme mitigates the potential information loss that is commonly associated with various data augmentation techniques involving raw graph data, such as edge perturbation, node removal, and attribute masking. Second, we propose a CGCL model that can learn invariant graph representations. A cross-view training scheme is proposed to train the proposed CGCL model. This scheme attempts to maximize the consistency information between one augmented view and the graph structure reconstructed from the other augmented view. Furthermore, we offer a comprehensive theoretical CGCL analysis. This paper empirically and experimentally demonstrates the effectiveness of the proposed CGCL method, achieving competitive results on graph datasets in comparisons with several state-of-the-art algorithms., Comment: 8 pages

Proportional-Integral-Derivative (PID) control has been the workhorse of control technology for about a century. Yet to this day, designing and tuning PID controllers relies mostly on either tabulated rules (Ziegler-Nichols) or on classical graphical techniques (Bode). Our goal in this paper is to take a fresh look on PID control in the context of optimizing stability margins for low-order (first- and second-order) linear time-invariant systems. Specifically, we seek to derive explicit expressions for gain and phase margins that are achievable using PID control, and thereby gain insights on the role of unstable poles and nonminimum-phase zeros in attaining robust stability. In particular, stability margins attained by PID control for minimum-phase systems match those obtained by more general control, while for nonminimum-phase systems, PID control achieves margins that are no worse than those of general control modulo a predetermined factor. Furthermore, integral action does not contribute to robust stabilization beyond what can be achieved by PD control alone.

This paper investigates the problem of data-driven stabilization for linear discrete-time switched systems with unknown switching dynamics. In the absence of noise, a data-based state feedback stabilizing controller can be obtained by solving a semi-definite program (SDP) on-the-fly, which automatically adapts to the changes of switching dynamics. However, when noise is present, the persistency of excitation condition based on the closed-loop data may be undermined, rendering the SDP infeasible. To address this issue, an auxiliary function-based switching control law is proposed, which only requires intermittent SDP solutions when its feasibility is guaranteed. By analyzing the relationship between the controller and the system switching times, it is shown that the proposed controller guarantees input-to-state practical stability (ISpS) of the closed-loop switched linear system, provided that the noise is bounded and the dynamics switches slowly enough. Two numerical examples are presented to verify the effectiveness of the proposed controller.

While most conversational agents are grounded on either free-text or structured knowledge, many knowledge corpora consist of hybrid sources. This paper presents the first conversational agent that supports the full generality of hybrid data access for large knowledge corpora, through a language we developed called SUQL (Structured and Unstructured Query Language). Specifically, SUQL extends SQL with free-text primitives (summary and answer), so information retrieval can be composed with structured data accesses arbitrarily in a formal, succinct, precise, and interpretable notation. With SUQL, we propose the first semantic parser, an LLM with in-context learning, that can handle hybrid data sources. Our in-context learning-based approach, when applied to the HybridQA dataset, comes within 8.9% exact match and 7.1% F1 of the SOTA, which was trained on 62K data samples. More significantly, unlike previous approaches, our technique is applicable to large databases and free-text corpora. We introduce a dataset consisting of crowdsourced questions and conversations on Yelp, a large, real restaurant knowledge base with structured and unstructured data. We show that our few-shot conversational agent based on SUQL finds an entity satisfying all user requirements 90.3% of the time, compared to 63.4% for a baseline based on linearization.

The rise of cyber-security concerns has brought significant attention to the analysis and design of cyber-physical systems (CPSs). Among the various types of cyberattacks, denial-of-service (DoS) attacks and false data injection (FDI) attacks can be easily launched and have become prominent threats. While resilient control against DoS attacks has received substantial research efforts, countermeasures developed against FDI attacks have been relatively limited, particularly when explicit system models are not available. To address this gap, the present paper focuses on the design of data-driven controllers for unknown linear systems subject to FDI attacks on the actuators, utilizing input-state data. To this end, a general FDI attack model is presented, which imposes minimally constraints on the switching frequency of attack channels and the magnitude of attack matrices. A dynamic state feedback control law is designed based on offline and online input-state data, which adapts to the channel switching of FDI attacks. This is achieved by solving two data-based semi-definite programs (SDPs) on-the-fly to yield a tight approximation of the set of subsystems consistent with both offline clean data and online attack-corrupted data. It is shown that under mild conditions on the attack, the proposed SDPs are recursively feasible and controller achieves exponential stability. Numerical examples showcase its effectiveness in mitigating the impact of FDI attacks.

The generation of nonuniform quadrupole states plays a crucial role in understanding various fascinating phenomena observed in the advancement of several research areas, e.g., multiferroic compounds, nonmagnetic superconductors, etc. In this work, we investigate the ground-state phase diagram of a generalized spin-3/2 bilinear-biquadratic-bicubic Heisenberg chain in the representation of multipolar operators. By numerical simulations with the large-scale density-matrix renormalization group (DMRG) method, we successfully identify a tetramerization phase and a stripe-Q phase. These phases are characterized by the emergence of nonuniform quadrupole orders resulting from the spontaneous breaking of translation symmetry. In particular, tetramerization phase refers to the quadrupole operators take a four-cycle, while the stripe-Q phase represents a striped pattern in quadrupole operators. Additionally, we demonstrate the presence of a Wess-Zumino-Witten (WZW) model with level k = 1 at the transition point between the dimerized (DM) phase and the Luttinger liquid (LL) phase, based on strong numerical findings.

Personal sound zone (PSZ) systems, which aim to create listening (bright) and silent (dark) zones in neighboring regions of space, are often based on time-varying acoustics. Conventional adaptive-based methods for handling PSZ tasks suffer from the collection and processing of acoustic transfer functions~(ATFs) between all the matching microphones and all the loudspeakers in a centralized manner, resulting in high calculation complexity and costly accuracy requirements. This paper presents a distributed pressure-matching (PM) method relying on diffusion adaptation (DPM-D) to spread the computational load amongst nodes in order to overcome these issues. The global PM problem is defined as a sum of local costs, and the diffusion adaption approach is then used to create a distributed solution that just needs local information exchanges. Simulations over multi-frequency bins and a computational complexity analysis are conducted to evaluate the properties of the algorithm and to compare it with centralized counterparts.

Observations of magnetic helicity transportation through the solar photosphere reflect the interaction of turbulent plasma movements and magnetic fields in the solar dynamo process. In this chapter, we have reviewed the research process of magnetic helicity inferred from the observed solar magnetic fields in the photosphere and also the solar morphological configurations with solar cycles. After introducing some achievements in the study of magnetic helicity, some key points would like to be summarized. The magnetic (current) helicity in the solar surface layer presents a statistical distribution similar to that of the sunspot butterfly diagram, but its maximum value is delayed from the extreme value of the sunspot butterfly diagram and corresponds in the phase with the statistical eruption of solar flares. During the spatial transport of magnetic (current) helicity from the interior of the sun into the interplanetary space at the time-space scale of the solar cycle, it shows the statistical distribution and the fluctuation with the hemispheric sign rule. These show that the current helicity and magnetic helicity transport calculation methods are complementary to each other. We also notice that the study of the inherent relationship between magnetic helicity and the solar cycle still depends on the observed accuracy of the solar magnetic field., Comment: 48 page,17 figures

This work explores the use of self-generated natural language explanations as an intermediate step for code-to-code translation with language models. Across three types of explanations and 19 programming languages constructed from the MultiPL-E dataset, we find the explanations to be particularly effective in the zero-shot case, improving performance by 12% on average. Improvements with natural language explanations are particularly pronounced on difficult programs. We release our dataset, code, and canonical solutions in all 19 languages., Comment: 9 pages, 4 figures, 5 tables, 48 pages total. To be published in EMNLP Findings 2023

Generative Face Video Coding (GFVC) techniques can exploit the compact representation of facial priors and the strong inference capability of deep generative models, achieving high-quality face video communication in ultra-low bandwidth scenarios. This paper conducts a comprehensive survey on the recent advances of the GFVC techniques and standardization efforts, which could be applicable to ultra low bitrate communication, user-specified animation/filtering and metaverse-related functionalities. In particular, we generalize GFVC systems within one coding framework and summarize different GFVC algorithms with their corresponding visual representations. Moreover, we review the GFVC standardization activities that are specified with supplemental enhancement information messages. Finally, we discuss fundamental challenges and broad applications on GFVC techniques and their standardization potentials, as well as envision their future trends. The project page can be found at https://github.com/Berlin0610/Awesome-Generative-Face-Video-Coding.

This paper considers self-triggered consensus control of unknown linear multi-agent systems (MASs). Self-triggering mechanisms (STMs) are widely used in MASs, thanks to their advantages in avoiding continuous monitoring and saving computing and communication resources. However, existing results require the knowledge of system matrices, which are difficult to obtain in real-world settings. To address this challenge, we present a data-driven approach to designing STMs for unknown MASs building upon the model-based solutions. Our approach leverages a system lifting method, which allows us to derive a data-driven representation for the MAS. Subsequently, a data-driven self-triggered consensus control (STC) scheme is designed, which combines a data-driven STM with a state feedback control law. We establish a data-based stability criterion for asymptotic consensus of the closed-loop MAS in terms of linear matrix inequalities, whose solution provides a matrix for the STM as well as a stabilizing controller gain. In the presence of external disturbances, a model-based STC scheme is put forth for $\mathcal{H}_{\infty}$-consensus of MASs, serving as a baseline for the data-driven STC. Numerical tests are conducted to validate the correctness of the data- and model-based STC approaches. Our data-driven approach demonstrates a superior trade-off between control performance and communication efficiency from finite, noisy data relative to the system identification-based one.

Difference features obtained by comparing the images of two periods play an indispensable role in the change detection (CD) task. However, a pair of bi-temporal images can exhibit diverse changes, which may cause various difference features. Identifying changed pixels with differ difference features to be the same category is thus a challenge for CD. Most nowadays' methods acquire distinctive difference features in implicit ways like enhancing image representation or supervision information. Nevertheless, informative image features only guarantee object semantics are modeled and can not guarantee that changed pixels have similar semantics in the difference feature space and are distinct from those unchanged ones. In this work, the generalized representation of various changes is learned straightforwardly in the difference feature space, and a novel Changes-Aware Transformer (CAT) for refining difference features is proposed. This generalized representation can perceive which pixels are changed and which are unchanged and further guide the update of pixels' difference features. CAT effectively accomplishes this refinement process through the stacked cosine cross-attention layer and self-attention layer. After refinement, the changed pixels in the difference feature space are closer to each other, which facilitates change detection. In addition, CAT is compatible with various backbone networks and existing CD methods. Experiments on remote sensing CD data set and street scene CD data set show that our method achieves state-of-the-art performance and has excellent generalization.

We study a large-scale patrol problem with state-dependent costs and multi-agent coordination.We consider heterogeneous agents, rather general reward functions, and the capabilities of tracking agents' trajectories.Given the complexity and uncertainty of the practical situations for patrolling, we model the problem as a discrete-time Markov decision process (MDP) that consists of a large number of parallel stochastic processes.We aim to minimize the cumulative patrolling cost over a finite time horizon.The problem exhibits an excessively large size of state space, which increases exponentially in the number of agents and the size of geographical region for patrolling.To reach practical solutions, we relax the dependencies between these parallel stochastic processes by randomizing all the state and action variables.In this context, the entire problem can be decomposed into a number of sub-problems, each of which has a much smaller state space and can be solved independently. The solutions of these sub-problems can lead to efficient heuristics.Unlike the past systems assuming relatively simple structure of the underlying stochastic process, here, tracking the patrol trajectories involves strong dependencies between the stochastic processes, leading to entirely different state and action spaces, transition kernels, and behaviours of processes,rendering the existing methods inapplicable or impractical.Further more, we prove that the performance deviation between the proposed policies and the possible optimal solution diminishes exponentially in the problem size, which also establishes the fact that the policies converge asymptotically at an exponential rate., Comment: 51 pages, 11 figures

We discuss the reconstruction of low-energy nuclear reaction kinematics from charged-particle tracks in solenoidal spectrometers working in Active Target Time Projection Chamber mode. In this operation mode, reaction products are tracked within the active gas medium of the Active Target with a three dimensional space point cloud. We have inferred the reaction kinematics from the point cloud using an algorithm based on a linear quadratic estimator (Kalman filter). The performance of this algorithm has been evaluated using experimental data from nuclear reactions measured with the Active Target Time Projection Chamber (AT-TPC) detector.

Despite substantial advances, single-image super-resolution (SISR) is always in a dilemma to reconstruct high-quality images with limited information from one input image, especially in realistic scenarios. In this paper, we establish a large-scale real-world burst super-resolution dataset, i.e., RealBSR, to explore the faithful reconstruction of image details from multiple frames. Furthermore, we introduce a Federated Burst Affinity network (FBAnet) to investigate non-trivial pixel-wise displacements among images under real-world image degradation. Specifically, rather than using pixel-wise alignment, our FBAnet employs a simple homography alignment from a structural geometry aspect and a Federated Affinity Fusion (FAF) strategy to aggregate the complementary information among frames. Those fused informative representations are fed to a Transformer-based module of burst representation decoding. Besides, we have conducted extensive experiments on two versions of our datasets, i.e., RealBSR-RAW and RealBSR-RGB. Experimental results demonstrate that our FBAnet outperforms existing state-of-the-art burst SR methods and also achieves visually-pleasant SR image predictions with model details. Our dataset, codes, and models are publicly available at https://github.com/yjsunnn/FBANet., Comment: Accepted by ICCV2023

Recent papers have used machine learning architecture to fit low-order functional ANOVA models with main effects and second-order interactions. These GAMI (GAM + Interaction) models are directly interpretable as the functional main effects and interactions can be easily plotted and visualized. Unfortunately, it is not easy to incorporate the monotonicity requirement into the existing GAMI models based on boosted trees, such as EBM (Lou et al. 2013) and GAMI-Lin-T (Hu et al. 2022). This paper considers models of the form $f(x)=\sum_{j,k}f_{j,k}(x_j, x_k)$ and develops monotone tree-based GAMI models, called monotone GAMI-Tree, by adapting the XGBoost algorithm. It is straightforward to fit a monotone model to $f(x)$ using the options in XGBoost. However, the fitted model is still a black box. We take a different approach: i) use a filtering technique to determine the important interactions, ii) fit a monotone XGBoost algorithm with the selected interactions, and finally iii) parse and purify the results to get a monotone GAMI model. Simulated datasets are used to demonstrate the behaviors of mono-GAMI-Tree and EBM, both of which use piecewise constant fits. Note that the monotonicity requirement is for the full model. Under certain situations, the main effects will also be monotone. But, as seen in the examples, the interactions will not be monotone., Comment: 12 pages

The prediction of molecular properties is a crucial task in the field of material and drug discovery. The potential benefits of using deep learning techniques are reflected in the wealth of recent literature. Still, these techniques are faced with a common challenge in practice: Labeled data are limited by the cost of manual extraction from literature and laborious experimentation. In this work, we propose a data-efficient property predictor by utilizing a learnable hierarchical molecular grammar that can generate molecules from grammar production rules. Such a grammar induces an explicit geometry of the space of molecular graphs, which provides an informative prior on molecular structural similarity. The property prediction is performed using graph neural diffusion over the grammar-induced geometry. On both small and large datasets, our evaluation shows that this approach outperforms a wide spectrum of baselines, including supervised and pre-trained graph neural networks. We include a detailed ablation study and further analysis of our solution, showing its effectiveness in cases with extremely limited data. Code is available at https://github.com/gmh14/Geo-DEG., Comment: 22 pages, 10 figures; ICML 2023

High Performance and Energy Efficiency are critical requirements for Internet of Things (IoT) end-nodes. Exploiting tightly-coupled clusters of programmable processors (CMPs) has recently emerged as a suitable solution to address this challenge. One of the main bottlenecks limiting the performance and energy efficiency of these systems is the instruction cache architecture due to its criticality in terms of timing (i.e., maximum operating frequency), bandwidth, and power. We propose a hierarchical instruction cache tailored to ultra-low-power tightly-coupled processor clusters where a relatively large cache (L1.5) is shared by L1 private caches through a two-cycle latency interconnect. To address the performance loss caused by the L1 capacity misses, we introduce a next-line prefetcher with cache probe filtering (CPF) from L1 to L1.5. We optimize the core instruction fetch (IF) stage by removing the critical core-to-L1 combinational path. We present a detailed comparison of instruction cache architectures' performance and energy efficiency for parallel ultra-low-power (ULP) clusters. Focusing on the implementation, our two-level instruction cache provides better scalability than existing shared caches, delivering up to 20\% higher operating frequency. On average, the proposed two-level cache improves maximum performance by up to 17\% compared to the state-of-the-art while delivering similar energy efficiency for most relevant applications., Comment: 14 pages