Search

Large Language Models (LLMs) have exhibited significant promise in recommender systems by empowering user profiles with their extensive world knowledge and superior reasoning capabilities. However, LLMs face challenges like unstable instruction compliance, modality gaps, and high inference latency, leading to textual noise and limiting their effectiveness in recommender systems. To address these challenges, we propose UserIP-Tuning, which uses prompt-tuning to infer user profiles. It integrates the causal relationship between user profiles and behavior sequences into LLMs' prompts. And employs expectation maximization to infer the embedded latent profile, minimizing textual noise by fixing the prompt template. Furthermore, A profile quantization codebook bridges the modality gap by categorizing profile embeddings into collaborative IDs, which are pre-stored for online deployment. This improves time efficiency and reduces memory usage. Experiments on four public datasets show that UserIP-Tuning outperforms state-of-the-art recommendation algorithms. Additional tests and case studies confirm its effectiveness, robustness, and transferability.

Recommender systems (RS) are vital for managing information overload and delivering personalized content, responding to users' diverse information needs. The emergence of large language models (LLMs) offers a new horizon for redefining recommender systems with vast general knowledge and reasoning capabilities. Standing across this LLM era, we aim to integrate recommender systems into a broader picture, and pave the way for more comprehensive solutions for future research. Therefore, we first offer a comprehensive overview of the technical progression of recommender systems, particularly focusing on language foundation models and their applications in recommendation. We identify two evolution paths of modern recommender systems -- via list-wise recommendation and conversational recommendation. These two paths finally converge at LLM agents with superior capabilities of long-term memory, reflection, and tool intelligence. Along these two paths, we point out that the information effectiveness of the recommendation is increased, while the user's acquisition cost is decreased. Technical features, research methodologies, and inherent challenges for each milestone along the path are carefully investigated -- from traditional list-wise recommendation to LLM-enhanced recommendation to recommendation with LLM agents. Finally, we highlight several unresolved challenges crucial for the development of future personalization technologies and interfaces and discuss the future prospects.

This paper introduces a random-batch molecular dynamics (RBMD) package for fast simulations of particle systems at the nano/micro scale. Different from existing packages, the RBMD uses random batch methods for nonbonded interactions of particle systems. The long-range part of Coulomb interactions is calculated in Fourier space by the random batch Ewald algorithm, which achieves linear complexity and superscalability, surpassing classical lattice-based Ewald methods. For the short-range part, the random batch list algorithm is used to construct neighbor lists, significantly reducing both computational and memory costs. The RBMD is implemented on GPU-CPU heterogeneous architectures, with classical force fields for all-atom systems. Benchmark systems are used to validate accuracy and performance of the package. Comparison with the particle-particle particle-mesh method and the Verlet list method in the LAMMPS package is performed on three different NVIDIA GPUs, demonstrating high efficiency of the RBMD on heterogeneous architectures. Our results also show that the RBMD enables simulations on a single GPU with a CPU core up to 10 million particles. Typically, for systems of one million particles, the RBMD allows simulating all-atom systems with a high efficiency of 8.20 ms per step, demonstrating the attractive feature for running large-scale simulations of practical applications on a desktop machine., Comment: 26 pages, 8 figures

Reranking is a critical component in recommender systems, playing an essential role in refining the output of recommendation algorithms. Traditional reranking models have focused predominantly on accuracy, but modern applications demand consideration of additional criteria such as diversity and fairness. Existing reranking approaches often fail to harmonize these diverse criteria effectively at the model level. Moreover, these models frequently encounter challenges with scalability and personalization due to their complexity and the varying significance of different reranking criteria in diverse scenarios. In response, we introduce a comprehensive reranking framework enhanced by LLM, designed to seamlessly integrate various reranking criteria while maintaining scalability and facilitating personalized recommendations. This framework employs a fully connected graph structure, allowing the LLM to simultaneously consider multiple aspects such as accuracy, diversity, and fairness through a coherent Chain-of-Thought (CoT) process. A customizable input mechanism is also integrated, enabling the tuning of the language model's focus to meet specific reranking needs. We validate our approach using three popular public datasets, where our framework demonstrates superior performance over existing state-of-the-art reranking models in balancing multiple criteria. The code for this implementation is publicly available.

As the demand for more personalized recommendation grows and a dramatic boom in commercial scenarios arises, the study on multi-scenario recommendation (MSR) has attracted much attention, which uses the data from all scenarios to simultaneously improve their recommendation performance. However, existing methods tend to integrate insufficient scenario knowledge and neglect learning personalized cross-scenario preferences, thus leading to suboptimal performance and inadequate interpretability. Meanwhile, though large language model (LLM) has shown great capability of reasoning and capturing semantic information, the high inference latency and high computation cost of tuning hinder its implementation in industrial recommender systems. To fill these gaps, we propose an effective efficient interpretable LLM-enhanced paradigm LLM4MSR in this work. Specifically, we first leverage LLM to uncover multi-level knowledge including scenario correlations and users' cross-scenario interests from the designed scenario- and user-level prompt without fine-tuning the LLM, then adopt hierarchical meta networks to generate multi-level meta layers to explicitly improves the scenario-aware and personalized recommendation capability. Our experiments on KuaiSAR-small, KuaiSAR, and Amazon datasets validate two significant advantages of LLM4MSR: (i) the effectiveness and compatibility with different multi-scenario backbone models (achieving 1.5%, 1%, and 40% AUC improvement on three datasets), (ii) high efficiency and deployability on industrial recommender systems, and (iii) improved interpretability. The implemented code and data is available to ease reproduction.

We primarily focus on the field of multi-scenario recommendation, which poses a significant challenge in effectively leveraging data from different scenarios to enhance predictions in scenarios with limited data. Current mainstream efforts mainly center around innovative model network architectures, with the aim of enabling the network to implicitly acquire knowledge from diverse scenarios. However, the uncertainty of implicit learning in networks arises from the absence of explicit modeling, leading to not only difficulty in training but also incomplete user representation and suboptimal performance. Furthermore, through causal graph analysis, we have discovered that the scenario itself directly influences click behavior, yet existing approaches directly incorporate data from other scenarios during the training of the current scenario, leading to prediction biases when they directly utilize click behaviors from other scenarios to train models. To address these problems, we propose the Multi-Scenario Causal-driven Adaptive Network M-scan). This model incorporates a Scenario-Aware Co-Attention mechanism that explicitly extracts user interests from other scenarios that align with the current scenario. Additionally, it employs a Scenario Bias Eliminator module utilizing causal counterfactual inference to mitigate biases introduced by data from other scenarios. Extensive experiments on two public datasets demonstrate the efficacy of our M-scan compared to the existing baseline models., Comment: This paper has been accepted by WWW'24

Recommender systems aim to predict user interest based on historical behavioral data. They are mainly designed in sequential pipelines, requiring lots of data to train different sub-systems, and are hard to scale to new domains. Recently, Large Language Models (LLMs) have demonstrated remarkable generalized capabilities, enabling a singular model to tackle diverse recommendation tasks across various scenarios. Nonetheless, existing LLM-based recommendation systems utilize LLM purely for a single task of the recommendation pipeline. Besides, these systems face challenges in presenting large-scale item sets to LLMs in natural language format, due to the constraint of input length. To address these challenges, we introduce an LLM-based end-to-end recommendation framework: UniLLMRec. Specifically, UniLLMRec integrates multi-stage tasks (e.g. recall, ranking, re-ranking) via chain-of-recommendations. To deal with large-scale items, we propose a novel strategy to structure all items into an item tree, which can be dynamically updated and effectively retrieved. UniLLMRec shows promising zero-shot results in comparison with conventional supervised models. Additionally, it boasts high efficiency, reducing the input token need by 86% compared to existing LLM-based models. Such efficiency not only accelerates task completion but also optimizes resource utilization. To facilitate model understanding and to ensure reproducibility, we have made our code publicly available.

Deep Recommender Systems (DRS) are increasingly dependent on a large number of feature fields for more precise recommendations. Effective feature selection methods are consequently becoming critical for further enhancing the accuracy and optimizing storage efficiencies to align with the deployment demands. This research area, particularly in the context of DRS, is nascent and faces three core challenges. Firstly, variant experimental setups across research papers often yield unfair comparisons, obscuring practical insights. Secondly, the existing literature's lack of detailed analysis on selection attributes, based on large-scale datasets and a thorough comparison among selection techniques and DRS backbones, restricts the generalizability of findings and impedes deployment on DRS. Lastly, research often focuses on comparing the peak performance achievable by feature selection methods, an approach that is typically computationally infeasible for identifying the optimal hyperparameters and overlooks evaluating the robustness and stability of these methods. To bridge these gaps, this paper presents ERASE, a comprehensive bEnchmaRk for feAture SElection for DRS. ERASE comprises a thorough evaluation of eleven feature selection methods, covering both traditional and deep learning approaches, across four public datasets, private industrial datasets, and a real-world commercial platform, achieving significant enhancement. Our code is available online for ease of reproduction., Comment: Accepted to KDD 2024

Environmental $\gamma$-rays constitute a crucial source of background in various nuclear, particle and quantum physics experiments. To evaluate the flux rate and the spectrum of $\gamma$ background, we have developed a novel and straightforward approach to reconstruct the environmental $\gamma$ flux spectrum by applying a portable CZT $\gamma$ detector and iterative Bayesian unfolding, which possesses excellent transferability for broader applications. In this paper, the calibration and GEANT4 Monte-Carlo modeling of the CZT detector, the unfolding procedure as well as the uncertainty estimation are demonstrated in detail. The reconstructed spectrum reveals an environmental $\gamma$ flux intensity of $3.3\pm 0.9\times 10^{7}$~ (m$^2\cdot$sr$\cdot$hour)$^{-1}$ ranging from 73 to 3033~keV, along with characteristic peaks primarily arising from $^{232}$Th series, $^{238}$U series and $^{40}$K. We also give an instance of background rate evaluation with the unfolded spectrum for validation of the approach.

Click-Through Rate (CTR) prediction is a crucial task in online recommendation platforms as it involves estimating the probability of user engagement with advertisements or items by clicking on them. Given the availability of various services like online shopping, ride-sharing, food delivery, and professional services on commercial platforms, recommendation systems in these platforms are required to make CTR predictions across multiple domains rather than just a single domain. However, multi-domain click-through rate (MDCTR) prediction remains a challenging task in online recommendation due to the complex mutual influence between domains. Traditional MDCTR models typically encode domains as discrete identifiers, ignoring rich semantic information underlying. Consequently, they can hardly generalize to new domains. Besides, existing models can be easily dominated by some specific domains, which results in significant performance drops in the other domains (i.e. the "seesaw phenomenon"). In this paper, we propose a novel solution Uni-CTR to address the above challenges. Uni-CTR leverages a backbone Large Language Model (LLM) to learn layer-wise semantic representations that capture commonalities between domains. Uni-CTR also uses several domain-specific networks to capture the characteristics of each domain. Note that we design a masked loss strategy so that these domain-specific networks are decoupled from backbone LLM. This allows domain-specific networks to remain unchanged when incorporating new or removing domains, thereby enhancing the flexibility and scalability of the system significantly. Experimental results on three public datasets show that Uni-CTR outperforms the state-of-the-art (SOTA) MDCTR models significantly. Furthermore, Uni-CTR demonstrates remarkable effectiveness in zero-shot prediction. We have applied Uni-CTR in industrial scenarios, confirming its efficiency., Comment: submited to TOIS

Estimating conditional average treatment effect from observational data is highly challenging due to the existence of treatment selection bias. Prevalent methods mitigate this issue by aligning distributions of different treatment groups in the latent space. However, there are two critical problems that these methods fail to address: (1) mini-batch sampling effects (MSE), which causes misalignment in non-ideal mini-batches with outcome imbalance and outliers; (2) unobserved confounder effects (UCE), which results in inaccurate discrepancy calculation due to the neglect of unobserved confounders. To tackle these problems, we propose a principled approach named Entire Space CounterFactual Regression (ESCFR), which is a new take on optimal transport in the context of causality. Specifically, based on the framework of stochastic optimal transport, we propose a relaxed mass-preserving regularizer to address the MSE issue and design a proximal factual outcome regularizer to handle the UCE issue. Extensive experiments demonstrate that our proposed ESCFR can successfully tackle the treatment selection bias and achieve significantly better performance than state-of-the-art methods., Comment: Accepted as NeurIPS 2023 Poster

In this letter, we study an unified resilient asymmetric bipartite consensus (URABC) problem for nonlinear multi-agent systems with both cooperative and antagonistic interactions under denial-of-service (DoS) attacks. We first prove that the URABC problem is solved by stabilizing the neighborhood asymmetric bipartite consensus error. Then, we develop a distributed compact form dynamic linearization method to linearize the neighborhood asymmetric bipartite consensus error. By using an extended discrete state observer to enhance the robustness against unknown dynamics and an attack compensation mechanism to eliminate the adverse effects of DoS attacks, we finally propose a distributed resilient model-free adaptive control algorithm to solve the URABC problem. A numerical example validates the proposed results.

Due to the nature of distributed secondary control paradigm, DC microgrids are prone to malicious cyber-physical attacks, which could be unbounded to maximize their damage. Existing resilient secondary control methods addressing unbounded attacks require that the first time derivatives of cyber-physical attack signals be bounded. The secondary defense strategy presented in this letter relax such a strict constraint by addressing more generally unbounded attack signals and hence, enhance the resilience of DC microgrids in adversarial environments. Rigorous proofs, based on Lyapunov techniques, show that the proposed method guarantees the uniformly ultimately bounded convergence for both voltage regulation and proportional load sharing under generally unbounded attacks. Comparative case studies further validate the enhanced resilience of the proposed attack-resilient control strategy.

This paper develops a fully distributed attack-resilient secondary defense strategies for AC microgrids, addressing more generally unbounded attacks on control input channels than those addressed in existing literature. The secondary control of local inverter includes consensus-based voltage and current regulators utilizing relative information from neighboring inverters. This distributed control approach relies on localized control and a sparse communication network, making it susceptible to malicious cyber-physical attacks that can impair consensus performance and potentially destabilize the overall microgrid. In contrast to existing solutions that are limited to addressing either bounded faults, noises or unbounded attacks with bounded first-order time derivatives, we aim to surpass these constraints and enhance the defense capabilities of counteracting cyber-physical attacks by enabling the AC microgrids adopting the proposed strategies to withstand a much wider range of unbounded cyber-attack signals. Fully distributed attack-resilient secondary defense strategies are developed for AC microgrids to counteract the detrimental effects of generally unbounded attacks on control input channels. Rigorous proofs using Lyapunov techniques demonstrate that the proposed defense strategies accomplish the uniformly ultimately bounded convergence on frequency regulation and achieve voltage containment and active power sharing simultaneously for multi-inverter-based AC microgrids in the face of generally unbounded attacks. The proposed defense strategies are validated on a modified IEEE 34-bus test feeder benchmark system incorporating four inverter-based DERs.

Multi-Domain Recommendation (MDR) has gained significant attention in recent years, which leverages data from multiple domains to enhance their performance concurrently.However, current MDR models are confronted with two limitations. Firstly, the majority of these models adopt an approach that explicitly shares parameters between domains, leading to mutual interference among them. Secondly, due to the distribution differences among domains, the utilization of static parameters in existing methods limits their flexibility to adapt to diverse domains. To address these challenges, we propose a novel model Hyper Adapter for Multi-Domain Recommendation (HAMUR). Specifically, HAMUR consists of two components: (1). Domain-specific adapter, designed as a pluggable module that can be seamlessly integrated into various existing multi-domain backbone models, and (2). Domain-shared hyper-network, which implicitly captures shared information among domains and dynamically generates the parameters for the adapter. We conduct extensive experiments on two public datasets using various backbone networks. The experimental results validate the effectiveness and scalability of the proposed model., Comment: Accepted by CIKM'2023

Click-Through Rate (CTR) prediction is a fundamental technique in recommendation and advertising systems. Recent studies have shown that implementing multi-scenario recommendations contributes to strengthening information sharing and improving overall performance. However, existing multi-scenario models only consider coarse-grained explicit scenario modeling that depends on pre-defined scenario identification from manual prior rules, which is biased and sub-optimal. To address these limitations, we propose a Scenario-Aware Hierarchical Dynamic Network for Multi-Scenario Recommendations (HierRec), which perceives implicit patterns adaptively and conducts explicit and implicit scenario modeling jointly. In particular, HierRec designs a basic scenario-oriented module based on the dynamic weight to capture scenario-specific information. Then the hierarchical explicit and implicit scenario-aware modules are proposed to model hybrid-grained scenario information. The multi-head implicit modeling design contributes to perceiving distinctive patterns from different perspectives. Our experiments on two public datasets and real-world industrial applications on a mainstream online advertising platform demonstrate that our HierRec outperforms existing models significantly.

Multi-task learning (MTL) aims at learning related tasks in a unified model to achieve mutual improvement among tasks considering their shared knowledge. It is an important topic in recommendation due to the demand for multi-task prediction considering performance and efficiency. Although MTL has been well studied and developed, there is still a lack of systematic review in the recommendation community. To fill the gap, we provide a comprehensive review of existing multi-task deep recommender systems (MTDRS) in this survey. To be specific, the problem definition of MTDRS is first given, and it is compared with other related areas. Next, the development of MTDRS is depicted and the taxonomy is introduced from the task relation and methodology aspects. Specifically, the task relation is categorized into parallel, cascaded, and auxiliary with main, while the methodology is grouped into parameter sharing, optimization, and training mechanism. The survey concludes by summarizing the application and public datasets of MTDRS and highlighting the challenges and future directions of the field.

Accurate local state measurement is important to ensure the reliable operation of distributed multi-agent systems (MAS). Existing fault-tolerant control strategies generally assume the sensor faults to be bounded and uncorrelated. In this paper, we study the ramifications of allowing the sensor attack injections to be unbounded and correlated. These malicious sensor attacks may bypass the conventional attack-detection methods and compromise the cooperative performance and even stability of the distributed networked MAS. Moreover, the attackers may gain access to the actuation computing channels and manipulate the control input commands. To this end, we consider the resilient containment control problem of general linear heterogeneous MAS in the face of correlated and unbounded sensor attacks, as well as general unbounded actuator attacks. We propose an attack-resilient control framework to guarantee the uniform ultimate boundedness of the closed-loop dynamical systems and preserve the bounded containment performance. Compared with existing literature addressing bounded faults and/or disturbances that are unintentionally caused in the sensor and actuator channels, the proposed control protocols are resilient against unknown unbounded attack signals simultaneously injected into sensor and actuator channels, and hence are more practical in the real-world security applications. A numerical example illustrates the efficacy of the proposed result, by highlighting the resilience improvement over the conventional cooperative control method.

In this paper, we present, Wi-Mesh, a WiFi vision-based 3D human mesh construction system. Our system leverages the advances of WiFi to visualize the shape and deformations of the human body for 3D mesh construction. In particular, it leverages multiple transmitting and receiving antennas on WiFi devices to estimate the two-dimensional angle of arrival (2D AoA) of the WiFi signal reflections to enable WiFi devices to see the physical environment as we humans do. It then extracts only the images of the human body from the physical environment and leverages deep learning models to digitize the extracted human body into a 3D mesh representation. Experimental evaluation under various indoor environments shows that Wi-Mesh achieves an average vertices location error of 2.81cm and joint position error of 2.4cm, which is comparable to the systems that utilize specialized and dedicated hardware. The proposed system has the advantage of re-using the WiFi devices that already exist in the environment for potential mass adoption. It can also work in non-line of sight (NLoS), poor lighting conditions, and baggy clothes, where the camera-based systems do not work well., Comment: SenSys 2022

Scoring a large number of candidates precisely in several milliseconds is vital for industrial pre-ranking systems. Existing pre-ranking systems primarily adopt the \textbf{two-tower} model since the ``user-item decoupling architecture'' paradigm is able to balance the \textit{efficiency} and \textit{effectiveness}. However, the cost of high efficiency is the neglect of the potential information interaction between user and item towers, hindering the prediction accuracy critically. In this paper, we show it is possible to design a two-tower model that emphasizes both information interactions and inference efficiency. The proposed model, IntTower (short for \textit{Interaction enhanced Two-Tower}), consists of Light-SE, FE-Block and CIR modules. Specifically, lightweight Light-SE module is used to identify the importance of different features and obtain refined feature representations in each tower. FE-Block module performs fine-grained and early feature interactions to capture the interactive signals between user and item towers explicitly and CIR module leverages a contrastive interaction regularization to further enhance the interactions implicitly. Experimental results on three public datasets show that IntTower outperforms the SOTA pre-ranking models significantly and even achieves comparable performance in comparison with the ranking models. Moreover, we further verify the effectiveness of IntTower on a large-scale advertisement pre-ranking system. The code of IntTower is publicly available\footnote{https://github.com/archersama/IntTower}, Comment: Accept by CIKM 2022 & DLP-KDD best paper

In recent years there has been substantial growth in the capabilities of systems designed to generate text that mimics the fluency and coherence of human language. From this, there has been considerable research aimed at examining the potential uses of these natural language generators (NLG) towards a wide number of tasks. The increasing capabilities of powerful text generators to mimic human writing convincingly raises the potential for deception and other forms of dangerous misuse. As these systems improve, and it becomes ever harder to distinguish between human-written and machine-generated text, malicious actors could leverage these powerful NLG systems to a wide variety of ends, including the creation of fake news and misinformation, the generation of fake online product reviews, or via chatbots as means of convincing users to divulge private information. In this paper, we provide an overview of the NLG field via the identification and examination of 119 survey-like papers focused on NLG research. From these identified papers, we outline a proposed high-level taxonomy of the central concepts that constitute NLG, including the methods used to develop generalised NLG systems, the means by which these systems are evaluated, and the popular NLG tasks and subtasks that exist. In turn, we provide an overview and discussion of each of these items with respect to current research and offer an examination of the potential roles of NLG in deception and detection systems to counteract these threats. Moreover, we discuss the broader challenges of NLG, including the risks of bias that are often exhibited by existing text generation systems. This work offers a broad overview of the field of NLG with respect to its potential for misuse, aiming to provide a high-level understanding of this rapidly developing area of research., Comment: Study completed by end of December 2021; 62 pages