Offline reinforcement learning (RL) is a useful approach for recommender systems because it can optimize long-term user feedback from logged interaction data without online exploration. A key challenge is the multi-modal nature of user preferences: a user may like several unrelated item types, so a unimodal policy (for example, a Gaussian) tends to average across modes and generate actions that do not match any interest. Recent diffusion-based policies can model complex preference distributions, but they often require many denoising steps. We propose PerfRec (Preference-aware Flow for Recommendation), a flow-matching offline RL framework that learns an expressive behavioral policy and distills it into an efficient one-step policy. PerfRec (i) trains a conditional flow model to clone the logged action distribution, (ii) trains twin Q-networks using next actions sampled from the learned flow policy, and (iii) trains an advantage-conditioned one-step policy with Q-guidance for improvement and a distillation loss that keeps the policy close to the flow policy. We use binary advantage conditioning to separate high-advantage and low-advantage regions of the flow-induced action distribution, so that at inference we can sample from the high-advantage mode with a single forward pass. Experiments on five benchmark datasets and one online simulation platform show that PerfRec improves recommendation performance over strong offline RL baselines.

Large language models (LLMs) have recently been adopted for recommendation by framing user preference modeling as a language generation problem. However, existing latent reasoning approaches typically represent user intent with a single latent vector, which struggles to capture the inherently multi-faceted nature of user preferences. We propose Factorized Latent Reasoning (FLR), a novel framework for LLM-based sequential recommendation that decomposes latent reasoning into multiple disentangled preference factors. FLR introduces a lightweight multi-factor attention module that iteratively refines a latent thought representation, where each factor attends to distinct aspects of the user's interaction history. To encourage diversity and specialization, we design orthogonality, attention diversity, and sparsity regularization objectives, and dynamically aggregate factor contributions for the final prediction. We further integrate FLR with an efficient reinforcement learning strategy based on group-relative policy optimization, enabling stable alignment directly in the latent reasoning space. Experiments on multiple benchmarks show that FLR consistently outperforms strong baselines while improving robustness and interpretability. Our data and code are available at https://github.com/ToAdventure/FLR.

Real-world document question-answering that relies on screenshots, such as bills and forms, requires evidence that is often spatially localised and visually cluttered. However, most Screenshot Language Models (SLMs) encode the entire page holistically and rely on implicit attention to ''find'' relevant content, which limits both accuracy and efficiency. We present RegionSLM, a region-aware SLM designed to explicitly connect the question to its supporting regions. RegionSLM has two key components: (1) a patch-relevance router that learns a query–region relevance distribution, enabling the model to produce a box-free relevance prior at inference; and (2) Relevance-Guided Region Pooling (RGRP), a query-conditional attention–pooling module that aggregates dense features into a small set of region tokens, which preserves grounding signals while reducing computational overhead. To support training and evaluation, we further curate ReDoc, a region-supervised corpus with 105k documents and 350k question-answer pairs, obtained via a question-guided two-step filtering procedure. Extensive experiments on 12 datasets demonstrate that explicitly learning query–region relevance and pooling it into compact region tokens is an effective and practical recipe for document retrieval and understanding.

Multimodal Retrieval-Augmented Generation (MRAG) addresses key limitations of Multimodal Large Language Models (MLLMs), such as hallucination and outdated knowledge. However, current MRAG systems struggle to distinguish whether retrieved multimodal data truly supports the semantic core of an answer or merely provides superficial relevance. Existing metrics often rely on heuristic position-based confidence, which fails to capture the informational density of multimodal entities. To address this, we propose Multi-modal Evidence Grounding (MEG), a semantic-aware metric that quantifies the contribution of retrieved evidence. Unlike standard confidence measures, MEG utilizes Semantic Certainty Anchoring, which dynamically filters out high-frequency stopwords via Inverse Document Frequency (IDF) to focus strictly on information-bearing tokens. Building on MEG, we introduce MEG-RAG, a framework that trains a multimodal reranker to align retrieved evidence with the semantic anchors of the ground truth. By prioritizing high-value content based on semantic grounding rather than token probability distributions, MEG-RAG improves the accuracy and multimodal consistency of generated outputs. Extensive experiments on the ??2RAG benchmark show that MEG-RAG consistently outperforms strong baselines and demonstrates robust generalization across different teacher models. The data and code are available at here.

The rapid advancement of large language models (LLMs) has opened new possibilities for understanding users in search and recommendation. While traditional behavior-based or feature-driven user models rely primarily on explicit interactions or handcrafted representations, LLMs introduce a fundamentally different paradigm: LLM-powered user profiling, where user preferences, intents, and contextual attributes can be extracted, summarized, or reasoned about directly through natural language. This shift unlocks powerful new paths to achieve personalization but also raises pressing questions related to modeling fidelity, temporal dynamics, evaluation methodology, privacy, and responsible deployment. The LLM-UP workshop aims to bring together researchers and practitioners to systematize emerging progress in LLM-powered user profiling, identify open challenges, and explore opportunities for integrating such techniques into search and recommendation pipelines. The LLM-UP workshop adopts an interactive structure featuring lightning talks, panel discussions, and paper presentations to foster active engagement, cross-disciplinary dialogue, and community-driven agenda setting for this rapidly evolving field.

Recent advancements in diffusion models have shown promising results in sequential recommendation (SR). Existing approaches predominantly rely on implicit conditional diffusion models, which compress user behaviors into a single representation during the forward diffusion process. While effective to some extent, this oversimplification often leads to the loss of sequential and contextual information, which is critical for understanding user behavior. Moreover, explicit information, such as user-item interactions or sequential patterns, remains underutilized, despite its potential to directly guide the recommendation process and improve precision. However, combining implicit and explicit information is non-trivial, as it requires dynamically integrating these complementary signals while avoiding noise and irrelevant patterns within user behaviors. To address these challenges, we propose Dual Conditional Diffusion Models for Sequential Recommendation (DCRec), which effectively integrates implicit and explicit information by embedding dual conditions into both the forward and reverse diffusion processes. This allows the model to retain valuable sequential and contextual information while leveraging explicit user-item interactions to guide the recommendation process. Specifically, we introduce the Dual Conditional Diffusion Transformer (DCDT), which dynamically integrate both implicit and explicit signals throughout the diffusion stages, ensuring contextual understanding and minimizing the influence of irrelevant patterns. Extensive experiments on public benchmark datasets demonstrate that DCRec significantly outperforms state-of-the-art methods.

Retrieval-augmented generation (RAG) has become a powerful framework for enhancing large language models in knowledge-intensive and reasoning tasks. However, as reasoning chains deepen or search trees expand, RAG systems often face two persistent failures: evidence forgetting, where retrieved knowledge is not effectively used, and inefficiency, caused by uncontrolled query expansions and redundant retrieval. These issues reveal a critical gap between retrieval and evidence utilization in current RAG architectures. We propose PruneRAG, a confidence-guided query decomposition framework that builds a structured query decomposition tree to perform stable and efficient reasoning. PruneRAG introduces three key mechanisms: adaptive node expansion that regulates tree width and depth, confidence-guided decisions that accept reliable answers and prune uncertain branches, and fine-grained retrieval that extracts entity-level anchors to improve retrieval precision. Together, these components preserve salient evidence throughout multi-hop reasoning while significantly reducing retrieval overhead. To better analyze evidence misuse, we define the Evidence Forgetting Rate as a metric to quantify cases where golden evidence is retrieved but not correctly used. Extensive experiments across various multi-hop QA benchmarks show that PruneRAG achieves superior accuracy and efficiency over state-of-the-art baselines. The code is publicly available.

Users increasingly interact with content across multiple domains, resulting in sequential behaviors marked by frequent and complex transitions. While Cross-Domain Sequential Recommendation (CDSR) models two-domain interactions, Multi-Domain Sequential Recommendation (MDSR) introduces significantly more domain transitions, compounded by challenges such as domain heterogeneity and imbalance. Existing approaches often overlook the intricacies of domain transitions, tend to overfit to dense domains while underfitting sparse ones, and struggle to scale effectively as the number of domains increases. We propose GMFlowRec, an efficient generative framework for MDSR that models domain-aware transition trajectories via Gaussian Mixture Flow Matching. GMFlowRec integrates: (1) a unified dual-masked Transformer to disentangle domain-invariant and domain-specific intents, (2) a Gaussian Mixture flow field to capture diverse behavioral patterns, and (3) a domain-aligned prior to support frequent and sparse transitions. Extensive experiments on JD and Amazon datasets show GMFlowRec achieves up to 44% NDCG@5 improvement over state-of-the-art baselines while maintaining efficiency with a single unified backbone. Our code and data are available here.

Long-term time series forecasting (LTSF) is fundamental to various real-world applications, where Transformer-based models have become the dominant framework due to their ability to capture long-range dependencies. However, these models often experience overfitting due to data redundancy in rolling forecasting settings, limiting their generalization ability particularly evident in longer sequences with highly similar adjacent data. In this work, we introduce CLMFormer, a novel framework that mitigates redundancy through curriculum learning and a memory-driven decoder. Specifically, we progressively introduce Bernoulli noise to the training samples, which effectively breaks the high similarity between adjacent data points. This curriculum-driven noise introduction aids the memory-driven decoder by supplying more diverse and representative training data, enhancing the decoder’s ability to model seasonal tendencies and dependencies in the time series data. To further enhance forecasting accuracy, we introduce a memory-driven decoder. This component enables the model to capture seasonal tendencies and dependencies in the time series data and leverages temporal relationships to facilitate the forecasting process. Extensive experiments on six real-world LTSF benchmarks show that CLMFormer consistently improves Transformer-based models by up to 30%, demonstrating its effectiveness in long-horizon forecasting.

Navigation is a fundamental task in the research of Embodied AI, and recent advances in machine learning algorithms have garnered growing interest in developing versatile Embodied AI systems. However, current research in this domain reveals opportunities for improvement. First, the direct application of RNNs and Transformers often overlooks the distinct characteristics of navigation tasks compared to traditional sequential data modeling. These methods are inherently designed to capture long-term dependencies, which are relatively weak in navigation scenarios, potentially limiting their performance in such tasks. Second, the reliance on task-specific configurations, such as pre-trained modules and dataset-specific logic, compromises the generalizability of these methods. We address these constraints by initially exploring the unique differences between Navigation tasks and other sequential data tasks through the lens of Causality, presenting a causal framework to elucidate the inadequacies of conventional sequential methods for Navigation. By leveraging this causal perspective, we propose Causality-Aware Transformer (CAT) Networks for Navigation, featuring a Causal Understanding Module to enhance the model’s Environmental Understanding capability. Meanwhile, our method is devoid of task-specific inductive biases and can be trained in an End-to-End manner, which enhances the method’s generalizability across various contexts. Empirical evaluations demonstrate that our methodology consistently surpasses benchmark performances across a spectrum of settings, tasks, and simulation environments, specifically, in Object Navigation within RoboTHOR, Objective Navigation, Point Navigation in Habitat, and R2R Navigation. Extensive ablation studies reveal that the performance gains can be attributed to the Causal Understanding Module, which demonstrates effectiveness and efficiency in both Reinforcement Learning and Supervised Learning settings. Additionally, further analysis highlights the robustness of our method, demonstrating its capacity to consistently perform well across diverse experimental settings and varying conditions. This robustness underscores the adaptability and generalizability of our approach, reinforcing its potential for application across a wide range of tasks.

Graph Neural Networks (GNNs) have been widely used for learning representations of graph-structured data, achieving remarkable success in various graph-related Web applications, such as fraud detection. To generate node representations, GNN-based models operate message-passing mechanisms that aim to smooth the learned representations in a local neighborhood. However, fraudsters increasingly employ sophisticated “camouflage” tactics, exhibiting normal behaviors by strategically forming numerous connections with legitimate entities. As a result, existing GNN-based methods struggle to effectively tackle such fraudulent activities due to their reliance on homophily-based message-passing architectures. These methods fail to generate discriminative representations, which is crucial for distinguishing fraudsters from benign entities. To address this problem, we propose a novel Discriminative Enhanced Aggregation Graph Neural Network-based FraudDEtectioNMoDel (DEFEND) . DEFEND incorporates tailored discriminative mechanisms that strengthen representation learning at two complementary levels: (i) intra-relation and (ii) inter-relation. While prior approaches primarily focus on intra-relation patterns and overlook inter-relation information, DEFEND integrates both to capture subtle inconsistencies in fraudster behavior. Specifically, an edge discriminating mechanism classifies neighborhoods into homophily or heterophily-based views by leveraging node attributes and structural characteristics, and a camouflage-aware dual-channel aggregation module captures different frequencies of information tailored to these views to generate rich intra-relation node representations. While prior approaches typically rely on intra-relation information within each relation type, they overlook the discriminative signals that arise from correlations across different relations. In DEFEND, we observe that fraudsters often avoid forming consistent cross-relation interactions, whereas benign entities tend to establish them more frequently. This discrepancy creates a distinctive behavioral pattern. To capture this, we introduce an inter-relation correlation mechanism that correlates a node’s intra-relation representations across multiple relation types using an attention-based weighting scheme. By adaptively weighing the importance of each relation and integrating their contributions, DEFEND enhances the discriminative power of node representations. This mechanism enables the model to leverage both intra-relation and inter-relation levels of information, leading to richer and more robust representations for fraud detection. Finally, a multi-relation combination module aggregates information across different relation types, emphasizing the importance of node–relation pairs in the embedding. We conducted extensive experiments on two real-world fraud datasets to demonstrate the effectiveness of our proposed model, and our results show that DEFEND outperforms the state-of-the-art baselines. The source codes and datasets of our work are available at https://github.com/VenusHaghighi/DEFEND .

Deep Reinforcement Learning (DRL) has garnered significant attention as a promising approach for developing intelligent and adaptive recommender systems. This paradigm is especially well-suited for recommendation scenarios characterized by dynamic user environments, temporally delayed feedback signals, and continuously shifting user preferences. However, deploying DRL within recommendation scenarios introduces a range of intricate challenges. These include the design of meaningful and task-aligned reward functions, effective navigation of vast and complex action spaces, and the need to maintain sample efficiency in data-sparse environments. Ensuring robust and stable training dynamics adds further difficulty. This special issue brings together a diverse collection of cutting-edge research that addresses these pressing challenges, showcasing advances that move the field toward more adaptive, robust, and personalized recommendation systems grounded in reinforcement learning.

Personal Knowledge Graphs (PKGs) organize an individual user's information into a structured format comprising entities, attributes, and relationships. By leveraging this structured and semantically rich data, PKGs have become essential for securing personal data management and delivering personalized services. To unlock their potential in personalized recommendations, prior research has explored the construction of PKGs and recommendation methods built upon them. However, these studies often overlook challenges associated with distributed PKGs across different users, such as joint training and privacy protection. To address these challenges, we propose PKGRec, a federated graph recommendation method specifically designed for PKGs, which utilizes a federated learning framework to ensure user privacy and data security during joint learning. Furthermore, to accommodate the user-centric graph structure of PKGs, our approach categorizes entities into three types: users, items, and other entities. It then applies a novel staged graph convolution method to model various entities based on these entity categories during local training. To enable efficient graph information sharing among distributed PKGs without requiring additional data transfer or aggregation, PKGRec performs graph expansion on the trained gradients by federated aggregation. Extensive experiments conducted on four publicly available datasets demonstrate that our method consistently outperforms the existing federated recommendation approaches.

Reinforcement learning-based recommender systems (RL4RS) have gained attention for their ability to adapt to dynamic user preferences. However, these systems face challenges, particularly in offline settings, where data inefficiency and reliance on pre-collected trajectories limit their broader applicability. While offline reinforcement learning methods leverage extensive datasets to address these issues, they often struggle with noisy data and fail to capture long-term user preferences, resulting in suboptimal recommendation policies. To overcome these limitations, we propose Diffusion-enhanced Actor-Critic for Offline RL4RS (DAC4Rec), a novel framework that integrates diffusion processes with reinforcement learning to model complex user preferences more effectively. DAC4Rec leverages the denoising capabilities of diffusion models to enhance the robustness of offline RL algorithms and incorporates a Q-value-guided policy optimization strategy to better handle suboptimal trajectories. Additionally, we introduce an energy-based sampling strategy to reduce randomness during recommendation generation, ensuring more targeted and reliable outcomes. We validate the effectiveness of DAC4Rec through extensive experiments on six real-world offline datasets and in an online simulation environment, demonstrating its ability to optimize long-term user preferences. Furthermore, we show that the proposed diffusion policy can be seamlessly integrated into other commonly used RL algorithms in RL4RS, highlighting its versatility and wide applicability.

Reinforcement Learning-based recommender systems (RLRS) offer an effective way to handle sequential recommendation tasks but often face difficulties in real-world settings, where user feedback data can be sub-optimal or sparse. In this paper, we introduce MDT4Rec, an offline RLRS framework that builds on the Decision Transformer (DT) to address two major challenges: learning from sub-optimal histories and representing complex user-item interactions. First, MDT4Rec shifts the trajectory stitching procedure from the training phase to action inference, allowing the system to shorten its historical context when necessary and thereby ignore negative or unsuccessful past experiences. Second, MDT4Rec initializes DT with a pre-trained large language model (LLM) for knowledge transfer, replaces linear embedding layers with Multi-Layer Perceptrons (MLPs) for more flexible representations, and employs Low-Rank Adaptation (LoRA) to efficiently fine-tune only a small subset of parameters. We evaluate MDT4Rec on five public datasets and in an online simulation environment, demonstrating that it outperforms existing methods.

Diffusion models (DMs) are powerful generative models capable of producing high-fidelity images but are constrained by high computational costs due to iterative multi-step inference. While Neural Architecture Search (NAS) can optimize DMs, existing methods are hindered by retraining requirements, exponential search complexity from step-wise optimization, and slow evaluation relying on massive image generation. To address these challenges, we propose Flexiffusion, a training-free NAS framework that jointly optimizes generation schedules and model architectures without modifying pre-trained parameters. Our key insight is to decompose the generation process into flexible segments of equal length, where each segment dynamically combines three step types: full (complete computation), partial (cache-reused computation), and null (skipped computation). This segment-wise search space reduces the candidate pool exponentially compared to step-wise NAS while preserving architectural diversity. Further, we introduce relative FID (rFID), a lightweight evaluation metric for NAS that measures divergence from a teacher model's outputs instead of ground truth, slashing evaluation time by over 90%. In practice, Flexiffusion achieves at least 2× acceleration across LDMs, Stable Diffusion, and DDPMs on ImageNet and MS-COCO, with FID degradation under 5%, outperforming prior NAS and caching methods. Notably, it attains 5.1× speedup on Stable Diffusion with near-identical CLIP scores. Our work pioneers a resource-efficient paradigm for searching high-speed DMs without sacrificing quality.

Controlling speaking style in text-to-speech (TTS) systems has become a growing focus in both academia and industry. While many existing approaches rely on reference audio to guide style generation, such methods are often impractical due to privacy concerns and limited accessibility. More recently, large language models (LLMs) have been used to control speaking style through natural language prompts; however, their high computational cost, lack of interpretability, and sensitivity to prompt phrasing limit their applicability in real-time and resource-constrained environments. In this work, we propose ParaStyleTTS, a lightweight and interpretable TTS framework that enables expressive style control from text prompts alone. ParaStyleTTS features a novel two-level style adaptation architecture that separates prosodic and paralinguistic speech style modeling. It allows fine-grained and robust control over factors such as emotion, gender, and age. Unlike LLM-based methods, ParaStyleTTS maintains consistent style realization across varied prompt formulations and is well-suited for real-world applications, including on-device and low-resource deployment. Experimental results show that ParaStyleTTS generates high-quality speech with performance comparable to state-of-the-art LLM-based systems while being 30x faster, using 8x fewer parameters, and requiring 2.5x less CUDA memory. Moreover, ParaStyleTTS exhibits superior robustness and controllability over paralinguistic speaking styles, providing a practical and efficient solution for style-controllable text-to-speech generation. Demo can be found at https://parastyletts.github.io/ParaStyleTTS_Demo/. Code can be found at https://github.com/haoweilou/ParaStyleTTS.

Human subjective evaluation plays a crucial role in evaluating speech-related generative tasks such as text-to-speech (TTS) generation. However, current practices are often constrained by limited scalability, fragmented workflows, and inconsistent rating reliability. Researchers frequently rely on manual methods or general-purpose crowdsourcing systems, where recruiting appropriately skilled listeners is challenging, and result analysis is labor-intensive. In this work, we introduce Achoio, a dedicated end-to-end online system designed to streamline and scale human evaluation for the TTS research community. Achoio allows researchers to create and manage evaluation projects, upload synthesized speech samples, and automatically match them with qualified listeners based on linguistic proficiency and domain knowledge. The system provides built-in tools for project status tracking, result aggregation and visualization. In this demonstration, we will walk through the core features of Achoio, including intuitive project setup, skill-based listener matching algorithm, and automated analytics. By addressing the limitations of existing workflows, Achoio offers a scalable, domain-aware, and analysis-ready solution for conducting high-quality subjective TTS evaluations. Our system is live and can be found at https://www.achoio.com. Demo is available on YouTube at https://youtu.be/Ugjj3_YooSM.

Sentiment bias is newly discovered in Recommender Systems (RSs). Critical users and niche items are disadvantaged by such unfair recommendations. To mitigate this bias, we propose a novel approach by counterfactual inference, which is implemented in two stages. Experiment results validate that our model achieves comparable performance in rating prediction, providing better recommendations and effectively mitigating sentiment bias. To the best of our knowledge, this is the first work to employ counterfactual inference on sentiment bias mitigation in RSs.

In the era of big data, data mining has become indispensable for uncovering hidden patterns and insights from vast and complex datasets. The integration of multimodal data sources further enhances its potential. Multimodal Federated Learning (MFL) is a distributed approach that enhances the efficiency and quality of multimodal learning, ensuring collaborative work and privacy protection. However, missing modalities pose a significant challenge in MFL, often due to data quality issues or privacy policies across the clients. In this work, we present MMiC, a framework for Mitigating Modality incompleteness in MFL within the Clusters. MMiC replaces partial parameters within client models inside clusters to mitigate the impact of missing modalities. Furthermore, it leverages the Banzhaf Power Index to optimize client selection under these conditions. Finally, MMiC employs an innovative approach to dynamically control global aggregation by utilizing Markovitz Portfolio Optimization. Extensive experiments demonstrate that MMiC consistently outperforms existing federated learning architectures in both global and personalized performance on multimodal datasets with missing modalities, confirming the effectiveness of our proposed solution. Our code is available at https://github.com/gotobcn8/MMiC.

Protein research is crucial in various scientific disciplines, but understanding their intricate structure-function relationships remains challenging. Recent advancements in Large Language Models (LLMs) have significantly improved the comprehension of task-specific knowledge, suggesting the potential for specialized ChatGPT-like systems in protein research to aid fundamental investigations. In this work, we introduce ProtChatGPT, which aims to learn and understand protein structures using natural language. ProtChatGPT enables users to upload proteins, ask questions, and engage in interactive conversations to produce comprehensive answers. The system comprises multi-level protein encoding, protein-language alignment, and instruction tuning of LLMs. A protein first undergoes multiple protein encoders and PLP-former to produce multi-level hybrid protein embeddings, which are then aligned through a Protein Context Gating (PCG) module with contrastive learning, and projected by an adapter to conform with the LLM. The LLM finally combines user questions with projected protein embeddings to generate informative answers. Experiments show that ProtChatGPT can produce promising responses to proteins and the corresponding user questions. We hope that ProtChatGPT could form the basis for further exploration and application in protein research. Code and our pre-trained model will be publicly available.

In offline reinforcement learning-based recommender systems (RLRS), learning effective state representations is crucial for capturing user preferences that directly impact long-term rewards. However, raw state representations often contain high-dimensional, noisy information and components that are not causally relevant to the reward. Additionally, missing transitions in offline data make it challenging to accurately identify features that are most relevant to user satisfaction. To address these challenges, we propose Policy-Guided Causal Representation (PGCR), a novel two-stage framework for causal feature selection and state representation learning in offline RLRS. In the first stage, we learn a causal feature selection policy that generates modified states by isolating and retaining only the causally relevant components (CRCs) while altering irrelevant components. This policy is guided by a reward function based on the Wasserstein distance, which measures the causal effect of state components on the reward and encourages the preservation of CRCs that directly influence user interests. In the second stage, we train an encoder to learn compact state representations by minimizing the mean squared error (MSE) loss between the latent representations of the original and modified states, ensuring that the representations focus on CRCs. We provide a theoretical analysis proving the identifiability of causal effects from interventions, validating the ability of PGCR to isolate critical state components for decision-making. Extensive experiments demonstrate that PGCR significantly improves recommendation performance, confirming its effectiveness for offline RL-based recommender systems.

Abstract Fraud detection in online networks has become increasingly challenging as fraudsters adopt sophisticated camouflage tactics to evade detection, making it imperative to combat their deceptive strategies. Graph-based fraud detection has gained significant attention in recent years, reflecting its growing potential to mitigate sophisticated fraudulent activities. The main objective of graph-based fraud detection is to distinguish between fraudsters and normal entities within graphs. While real-world networks contain complex, high-order relationships, existing graph-based fraud detection methods focus solely on pairwise interactions, overlooking non-pairwise relationships and the broader dependencies among entities within fraud graphs. Thus, we highlight the importance of exploring non-pairwise relationships to build a more effective fraud detection model. In this paper, we propose TROPICAL, a novel TRansfOrmer-based hyPergraph LearnIng framework for detecting CAmouflaged maLicious actors in online social networks. To capture comprehensive high-order relations, we construct a hypergraph from the original input graph. However, constructing the hypergraph can be computationally intensive. TROPICAL addresses this challenge by carefully selecting moderate hyperparameters, creating a balance between computational efficiency and effectively capturing high-order relationships. TROPICAL learns node representations by processing multiple hyperedge groups and incorporates positional encodings into the aggregated information to enhance their distinctiveness. The aggregated sequential information is then passed through a transformer encoder, enabling the model to generate rich, high-order representations to detect camouflaged fraudsters. Extensive experiments on two real-world datasets demonstrate TROPICAL’s superior performance compared to the state-of-the-art fraud detection models. The source codes and the datasets of our work are available at https://github.com/VenusHaghighi/TROPICAL .

Reinforcement Learning-Based Recommender Systems (RLRS) have shown promise across a spectrum of applications, from e-commerce platforms to streaming services. Yet, they grapple with challenges, notably in crafting reward functions and harnessing large pre-existing datasets within the RL framework. Recent advancements in offline RLRS provide a solution for how to address these two challenges. However, existing methods mainly rely on the transformer architecture, which, as sequence lengths increase, can introduce challenges associated with computational resources and training costs. Additionally, the prevalent methods employ fixed-length input trajectories, restricting their capacity to capture evolving user preferences. In this study, we introduce a new offline RLRS method to deal with the above problems. We reinterpret the RLRS challenge by modeling sequential decision-making as an inference task, leveraging adaptive masking configurations. This adaptive approach selectively masks input tokens, transforming the recommendation task into an inference challenge based on varying token subsets, thereby enhancing the agent’s ability to infer across diverse trajectory lengths. Furthermore, we incorporate a multi-scale segmented retention mechanism that facilitates efficient modeling of long sequences, significantly enhancing computational efficiency. Our experimental analysis, conducted on both online simulator and offline datasets, clearly demonstrates the advantages of our proposed method.

The intelligent dialogue system, aiming at communicating with humans harmoniously with natural language, is brilliant for promoting the advancement of human-machine interaction in the era of artificial intelligence. With the gradually complex human-computer interaction requirements, it is difficult for traditional text-based dialogue system to meet the demands for more vivid and convenient interaction. Consequently, Visual-Context Augmented Dialogue (VAD) System, which has the potential to communicate with humans by perceiving and understanding multimodal information (i.e., visual context in images or videos, textual dialogue history), has become a predominant research paradigm. Benefiting from the consistency and complementarity between visual and textual context, VAD possesses the potential to generate engaging and context-aware responses. To depict the development of VAD, we first characterize the concept model of VAD and then present its generic system architecture to illustrate the system workflow, followed by a summary of multimodal fusion techniques. Subsequently, several research challenges and representative works are investigated, followed by the summary of authoritative benchmarks and real-world application of VAD. We conclude this article by putting forward some open issues and promising research trends for VAD, e.g., the cognitive mechanisms of human-machine dialogue under cross-modal dialogue context, mobile and lightweight deployment of VAD.

Federated learning (FL) is a distributed machine learning paradigm in which clients collaboratively train models in a privacy-preserving manner. While centralized FL (CFL) suffers from single points of failure and performance bottlenecks, decentralized FL (DFL), which depends on inter-client communication, has emerged to eliminate the need of a central entity. However, due to lack of the coordination of a central server, heterogeneous data distribution across clients makes local models in DFL inclined to diverge towards their local objectives, resulting in poor model accuracy. Moreover, each client in DFL needs to communicate with multiple neighbors, yielding a heavy communication load. To tackle these challenges, we propose a novel DFL framework called DFLStar, which can improve DFL from two perspectives. First, to avoid significantly diverging towards local data, DFLStar incorporates self-knowledge distillation to enhance the local model training by assimilating knowledge from the aggregated model. Second, clients in DFLStar identify and only select the most informative neighbors (based on the last layer model similarity) for parameter exchange, thereby minimizing the communication overhead. Our experimental results on two real datasets demonstrate that DFLStar significantly improves both communication overhead and training time compared to traditional DFL algorithms while achieving a specific target accuracy. Furthermore, within a fixed training duration, DFLStar constantly obtains the highest model accuracy compared to the baselines.

In Reinforcement Learning-based Recommender Systems (RLRS), the complexity and dynamism of user interactions often result in high-dimensional and noisy state spaces, making it challenging to discern which aspects of the state are truly influential in driving the decision-making process. This issue is exacerbated by the evolving nature of user preferences and behaviors, requiring the recommender system to adaptively focus on the most relevant information for decision-making while preserving generaliability. To tackle this problem, we introduce an innovative causal approach for decomposing the state and extracting Causal-InDispensable State Representations (CIDS) in RLRS. Our method concentrates on identifying the Directly Action-Influenced State Variables (DAIS) and Action-Influence Ancestors (AIA), which are essential for making effective recommendations. By leveraging conditional mutual information, we develop a framework that not only discerns the causal relationships within the generative process but also isolates critical state variables from the typically dense and high-dimensional state representations. We provide theoretical evidence for the identifiability of these variables. Then, by making use of the identified causal relationship, we construct causal-indispensable state representations, enabling the training of policies over a more advantageous subset of the agent's state space. We demonstrate the efficacy of our approach through extensive experiments, showcasing our method outperforms state-of-the-art methods.

The inclusion of the images opens up a security vulnerability of visually-aware recommender systems (VARSs). It can be exploited by unscrupulous parties to upload well-crafted adversarial images for certain malicious purposes (e.g., promoting their own products for profits). Some studies have focused on attacking VARSs to gain insights into their robustness, while they are still far from practical, i.e., the attacks often 1) lack diversity in perturbations, 2) are easily perceived and 3) have limited transferability, which may lead to overestimation of defenses in practice. To tackle the problems, we propose to perturb the style of the product, which is an unnoticeable but important property of visual recommendations. Specifically, we propose a novel Style perturbation-based Practical Attack Framework (SPAF). Unlike existing attacks that change pixels within l∞ -norm constraints, SPAF interferes with styles in latent feature space so that the attack becomes unbounded in the pixel space to reflect possible actual perturbations. SPAF formulates attack objectives as an optimization problem and adopts an adaptive adversarial style transfer network to solve it so that transferable and imperceptible attacks can be generated. Comprehensive experiments on real-world datasets demonstrate that SPAF significantly outperforms state-of-the-art attacks.

Graph-based fraud detection has attracted increasing attention in recent years, reflecting its growing potential in mitigating sophisticated fraudulent activities. The main objective of graph-based fraud detection is to discern between fraud-sters and normal entities within graphs. As fraudsters adopt increasingly sophisticated camouflage tactics, combating them has become an urgent task. Despite the complex interactions within real-world networks involving high-order relations, ex-isting graph-based fraud detection methods often neglect non-pairwise relationships among entities in graphs. Thus, we empha-size the significance of investigating beyond pairwise relationships for building an effective fraud detection model. In this paper, we propose constructing a hypergraph from the original input graph to encapsulate comprehensive high-order relations and present TROPICAL, a novel TRansfOrmer-based hyPergraph LearnIng for detecting CAmouflaged maLicious actors in online social networks. TROPICAL learns representations by processing different hyperedge groups and incorporates positional encodings into the aggregated information to enhance their distinctiveness. Subsequently, the model feeds the learned aggregated sequential information into the transformer encoder, achieving rich rep-resentations for effective camouflaged fraudster detection. The superiority of TROPICAL is demonstrated through experiments conducted on two real-world datasets, compared against the state-of-the-art fraud detection models. The source codes and datasets of our work are available at https://github.comNenusHaghighi/TROPICAL.

Reinforcement learning-based recommender systems have recently gained popularity. However, due to the typical limitations of simulation environments (e.g., data inefficiency), most of the work cannot be broadly applied in all domains. To counter these challenges, recent advancements have leveraged offline reinforcement learning methods, notable for their data-driven approach utilizing offline datasets. A prominent example of this is the Decision Transformer. Despite its popularity, the Decision Transformer approach has inherent drawbacks, particularly evident in recommendation methods based on it. This paper identifies two key shortcomings in existing Decision Transformer-based methods: a lack of stitching capability and limited effectiveness in online adoption. In response, we introduce a novel methodology named Max-Entropy enhanced Decision Transformer with Reward Relabeling for Offline RLRS (EDT4Rec). Our approach begins with a max entropy perspective, leading to the development of a max-entropy enhanced exploration strategy. This strategy is designed to facilitate more effective exploration in online environments. Additionally, to augment the model's capability to stitch sub-optimal trajectories, we incorporate a unique reward relabeling technique. To validate the effectiveness and superiority of EDT4Rec, we have conducted comprehensive experiments across six real-world offline datasets and in an online simulator.

The advancements in disentangled representation learning significantly enhance the accuracy of counterfactual predictions by granting precise control over instrumental variables, confounders, and adjustable variables. An appealing method for achieving the independent separation of these factors is mutual information minimization, a task that presents challenges in numerous machine learning scenarios, especially within high-dimensional spaces. To circumvent this challenge, we propose the Self-Distilled Disentanglement framework, referred to as SD2. Grounded in information theory, it ensures theoretically sound independent disentangled representations without intricate mutual information estimator designs for high-dimensional representations. Our comprehensive experiments, conducted on both synthetic and real-world datasets, confirms the effectiveness of our approach in facilitating counterfactual inference in the presence of both observed and unobserved confounders.

Cross-Domain Recommendation~(CDR) seeks to enable effective knowledge transfer across domains. Most existing works rely on either representation alignment or transformation bridges, but they come with shortcomings regarding identifiability of domain-shared and domain-specific latent factors. Specifically, while CDR describes user representations as a joint distribution over two domains, these methods fail to account for its joint identifiability as they primarily fixate on the marginal distribution within a particular domain. Such a failure may overlook the conditionality between two domains and how it contributes to latent factor disentanglement, leading to negative transfer when domains are weakly correlated. In this study, we explore what should and should not be transferred in cross-domain user representations from a causality perspective. We propose a Hierarchical causal subspace disentanglement approach to explore the Joint IDentifiability of cross-domain joint distribution, termed HJID, to preserve domain-specific behaviors from domain-shared factors. HJID abides by the feature hierarchy and divides user representations into generic shallow subspace and domain-oriented deep subspaces. We first encode the generic pattern in the shallow subspace by minimizing the Maximum Mean Discrepancy of initial layer activation. Then, to dissect how domain-oriented latent factors are encoded in deeper layers activation, we construct a cross-domain causality-based data generation graph, which identifies cross-domain consistent and domain-specific components, adhering to the Minimal Change principle. This allows HJID to maintain stability whilst discovering unique factors for different domains, all within a generative framework of invertible transformations that guarantee the joint identifiability. With experiments on real-world datasets, we show that HJID outperforms SOTA methods on both strong- and weak-correlation CDR tasks.

Recent years have seen the explosion of edge intelligence with powerful Deep Neural Networks (DNNs). One popular scheme is training DNNs on powerful cloud servers and subsequently porting them to mobile devices after being lightweight. Conventional approaches manually specialized DNNs for various edge platforms and retrain them with real-world data. However, as the number of platforms increases, these approaches become labour-intensive and computationally prohibitive. Additionally, real-world data tends to be sparse-label, further increasing the difficulty of lightweight models. In this paper, we propose MatchNAS, a novel scheme for porting DNNs to mobile devices. Specifically, we simultaneously optimise a large network family using both labelled and unlabelled data and then automatically search for tailored networks for different hardware platforms. MatchNAS acts as an intermediary that bridges the gap between cloud-based DNNs and edge-based DNNs.

introduction Free Access Share on Just AcceptedSpecial Issue on Responsible Recommender Systems Part 1 Authors: Lina Yao CSIRO's Data61 and University of New South Wales, Australia CSIRO's Data61 and University of New South Wales, Australia 0000-0002-4149-839XSearch about this author , Julian McAuley University of California, USA University of California, USASearch about this author , Xianzhi Wang University of Technology Sydney, Australia University of Technology Sydney, Australia 0000-0001-9582-3445Search about this author , Dietmar Jannach University of Klagenfurt, Austria University of Klagenfurt, Austria 0000-0002-4698-8507Search about this author Authors Info & Claims ACM Transactions on Intelligent Systems and TechnologyAccepted on April 2024https://doi.org/10.1145/3663528Online AM:15 June 2024Publication History 0citation5DownloadsMetricsTotal Citations0Total Downloads5Last 12 Months5Last 6 weeks5 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Publisher SiteeReaderPDF

Trajectory prediction is fundamental to various intelligent technologies, such as autonomous driving and robotics. The motion prediction of pedestrians and vehicles helps emergency braking, reduces collisions, and improves traffic safety. Current trajectory prediction research faces problems of complex social interactions, high dynamics and multi-modality. Especially, it still has limitations in long-time prediction. We propose Attention-aware Social Graph Transformer Networks for multi-modal trajectory prediction. We combine Graph Convolutional Networks and Transformer Networks by generating stable resolution pseudo-images from Spatio-temporal graphs through a designed stacking and interception method. Furthermore, we design the attention-aware module to handle social interaction information in scenarios involving mixed pedestrian-vehicle traffic. Thus, we maintain the advantages of the Graph and Transformer, i.e., the ability to aggregate information over an arbitrary number of neighbors and the ability to perform complex time-dependent data processing. We conduct experiments on datasets involving pedestrian, vehicle, and mixed trajectories, respectively. Our results demonstrate that our model minimizes displacement errors across various metrics and significantly reduces the likelihood of collisions. It is worth noting that our model effectively reduces the final displacement error, illustrating the ability of our model to predict for a long time.

Reinforcement learning serves as a potent tool for modeling dynamic user interests within recommender systems, garnering increasing research attention of late. However, a significant drawback persists: its poor data efficiency, stemming from its interactive nature. The training of reinforcement learning-based recommender systems demands expensive online interactions to amass adequate trajectories, essential for agents to learn user preferences. This inefficiency renders reinforcement learning-based recommender systems a formidable undertaking, necessitating the exploration of potential solutions. Recent strides in offline reinforcement learning present a new perspective. Offline reinforcement learning empowers agents to glean insights from offline datasets and deploy learned policies in online settings. Given that recommender systems possess extensive offline datasets, the framework of offline reinforcement learning aligns seamlessly. Despite being a burgeoning field, works centered on recommender systems utilizing offline reinforcement learning remain limited. This survey aims to introduce and delve into offline reinforcement learning within recommender systems, offering an inclusive review of existing literature in this domain. Furthermore, we strive to underscore prevalent challenges, opportunities, and future pathways, poised to propel research in this evolving field.

Neural Processes (NPs) are a family of supervised density estimators devoted to probabilistic function approximation with meta-learning. Despite extensive research on the subject, the absence of a unified framework for NPs leads to varied architectural solutions across diverse studies. This non-consensus poses challenges to reproducing and benchmarking different NPs. Moreover, existing codebases mainly prioritize generative density estimation, yet rarely consider expanding the capability of NPs to self-supervised representation learning, which however has gained growing importance in data mining applications. To this end, we present NP-SSL, a modular and configurable framework with built-in support, requiring minimal effort to 1) implement classical NPs architectures; 2) customize specific components; 3) integrate hybrid training scheme (e.g., contrastive); and 4) extend NPs to act as a self-supervised learning toolkit, producing latent representations of data, and facilitating diverse downstream predictive tasks. To illustrate, we discuss a case study that applies NP-SSL to model time-series data. We interpret that NP-SSL can handle different predictive tasks such as imputation and forecasting, by a simple switch in data samplings, without significant change to the underlying structure. We hope this study can reduce the workload of future research on leveraging NPs to tackle more a broader range of real-world data mining applications. Code and documentation are at https://github.com/zyecs/NP-SSL.

The field of generating recommendations within the framework of causal inference has seen a recent surge.This approach enhances insights into the influence of recommendations on user behavior and helps in identifying the underlying factors. Existing research has often leveraged propensity scores to mitigate bias, albeit at the risk of introducing additional variance. Others have explored the use of unbiased data from randomized controlled trials, although this comes with assumptions that may prove challenging in practice. In this paper, we first present the causality-aware interpretation of recommendations and reveal how the underlying exposure mechanism can bias the maximum likelihood estimation (MLE) of observational feedback. Recognizing that confounders may be elusive, we propose a contrastive self-supervised learning to minimize exposure bias, employing inverse propensity scores and expanding the positive sample set. Building on this foundation, we present a novel contrastive counterfactual learning method (CCL) that incorporates three unique positive sampling strategies grounded in estimated exposure probability or random counterfactual samples. Through extensive experiments on two real-world datasets, we demonstrate that our CCL outperforms the state-of-the-art methods.

Learning accurate cross-domain preference mappings in the absence of overlapped users/items has presented a persistent challenge in Non-overlapping Cross-domain Recommendation (NOCDR). Despite the efforts made in previous studies to address NOCDR, several limitations still exist. Specifically, 1) while some approaches substitute overlapping users/items with overlapping behaviors, they cannot handle NOCDR scenarios where such auxiliary information is unavailable; 2) often, cross-domain preference mapping is modeled by learning deterministic explicit representation matchings between sampled users in two domains. However, this can be biased due to individual preferences and thus fails to incorporate preference continuity and universality of the general population. In light of this, we assume that despite the scattered nature of user behaviors, there exists a consistent latent preference distribution shared among common people. Modeling such distributions further allows us to capture the continuity in user behaviors within each domain and discover preference invariance across domains. To this end, we propose a Distributional domain-invariant Preference Matching method for non-overlapping Cross-Domain Recommendation (DPMCDR). For each domain, we hierarchically approximate a posterior of domain-level preference distribution with empirical evidence derived from user-item interactions. Next, we aim to build distributional implicit matchings between the domain-level preferences of two domains. This process involves mapping them to a shared latent space and seeking a consensus on domain-invariant preference by minimizing the distance between their distributional representations therein. In this way, we can identify the alignment of two non-overlapping domains if they exhibit similar patterns of domain-invariant preference. Experiments on real-world datasets demonstrate that DPMCDR outperforms the state-of-the-art approaches with a range of evaluation metrics.

Recent studies have shown that recommender systems (RSs) are highly vulnerable to data poisoning attacks. Understanding attack tactics helps improve the robustness of RSs. We intend to develop efficient attack methods that use limited resources to generate high-quality fake user profiles to achieve 1) transferability among black-box RSs 2) and imperceptibility among detectors. In order to achieve these goals, we introduce textual reviews of products to enhance the generation quality of the profiles. Specifically, we propose a novel attack framework named R-Trojan, which formulates the attack objectives as an optimization problem and adopts a tailored transformer-based generative adversarial network (GAN) to solve it so that high-quality attack profiles can be produced. Comprehensive experiments on real-world datasets demonstrate that R-Trojan greatly outperforms state-of-the-art attack methods on various victim RSs under black-box settings and show its good imperceptibility.

Cross-Domain Sequential Recommendation(CDSR) aims to generate accurate predictions for future interactions by leveraging users’ cross-domain historical interactions. One major challenge of CDSR is how to jointly learn the single- and cross-domain user preferences efficiently. To enhance the target domain’s performance, most existing solutions start by learning the single-domain user preferences within each domain and then transferring the acquired knowledge from the rich domain to the target domain. However, this approach ignores the inter-sequence item relationship and also limits the opportunities for target domain knowledge to enhance the rich domain performance. Moreover, it also ignores the information within the cross-domain sequence. Despite cross-domain sequences being generally noisy and hard to learn directly, they contain valuable user behavior patterns with great potential to enhance performance. Another key challenge of CDSR is data sparsity, which also exists in other recommendation system problems. In the real world, the data distribution of the recommendation system is highly skewed to the popular products, especially on the large-scale dataset with millions of users and items. One more challenge is the class imbalance problem, inherited by the sequential recommendation problem. Generally, each sample only has one positive and thousands of negative samples. To address the above problems together, an innovative Decoupled Representation via Extraction Attention Module (DREAM) is proposed for CDSR to simultaneously learn single- and cross-domain user preference via decoupled representations. A novel Supervised Contrastive Learning framework is introduced to model the inter-sequence relationship as well as address the data sparsity via data augmentations. DREAM also leverages Focal Loss to put more weight on misclassified samples to address the class-imbalance problem, with another uplift on the overall model performance. Extensive experiments had been conducted on two cross-domain recommendation datasets, demonstrating DREAM outperforms various SOTA cross-domain recommendation algorithms achieving up to a 75% uplift in Movie-Book Scenarios.

Sequential recommender systems (SRSs) aim to predict the subsequent items which may interest users via comprehensively modeling users' complex preference embedded in the sequence of user-item interactions. However, most of existing SRSs often model users' single low-level preference based on item ID information while ignoring the high-level preference revealed by item attribute information, such as item category. Furthermore, they often utilize limited sequence context information to predict the next item while overlooking richer inter-item semantic relations. To this end, in this paper, we proposed a novel hierarchical preference modeling framework to substantially model the complex low- and high-level preference dynamics for accurate sequential recommendation. Specifically, in the framework, a novel dual-transformer module and a novel dual contrastive learning scheme have been designed to discriminatively learn users' low- and high-level preference and to effectively enhance both low- and high-level preference learning respectively. In addition, a novel semantics-enhanced context embedding module has been devised to generate more informative context embedding for further improving the recommendation performance. Extensive experiments on six real-world datasets have demonstrated both the superiority of our proposed method over the state-of-the-art ones and the rationality of our design.

Reinforcement learning-based recommender systems have recently gained popularity. However, the design of the reward function, on which the agent relies to optimize its recommendation policy, is often not straightforward. Exploring the causality underlying users' behavior can take the place of the reward function in guiding the agent to capture the dynamic interests of users. Moreover, due to the typical limitations of simulation environments (e.g., data ineffi- ciency), most of the work cannot be broadly applied in large-scale situations. Although some works attempt to convert the offline dataset into a simulator, data inefficiency makes the learning pro- cess even slower. Because of the nature of reinforcement learning (i.e., learning by interaction), it cannot collect enough data to train during a single interaction. Furthermore, traditional reinforcement learning algorithms do not have a solid capability like supervised learning methods to learn from offline datasets directly. In this paper, we propose a new model named the causal decision transformer for recommender systems (CDT4Rec). CDT4Rec is an offline reinforce- ment learning system that can learn from a dataset rather than from online interaction. Moreover, CDT4Rec employs the transformer architecture, which is capable of processing large offline datasets and capturing both short-term and long-term dependencies within the data to estimate the causal relationship between action, state, and reward. To demonstrate the feasibility and superiority of our model, we have conducted experiments on six real-world offline datasets and one online simulator.

Recommendation models are typically trained on observational user interaction data, but the interactions between latent factors in users' decision-making processes lead to complex and entangled data. Disentangling these latent factors to uncover their underlying representation can improve the robustness, interpretability, and controllability of recommendation models. This paper introduces the Causal Disentangled Variational Auto-Encoder (CaD-VAE), a novel approach for learning causal disentangled representations from interaction data in recommender systems. The CaD-VAE method considers the causal relationships between semantically related factors in real-world recommendation scenarios, rather than enforcing independence as in existing disentanglement methods. The approach utilizes structural causal models to generate causal representations that describe the causal relationship between latent factors. The results demonstrate that CaD-VAE outperforms existing methods, offering a promising solution for disentangling complex user behavior data in recommendation systems.

Recent sequential recommendation models rely increasingly on consecutive short-term user-item interaction sequences to model user interests. These approaches have, however, raised concerns about both short- and long-term interests. (1) short-term: interaction sequences may not result from a monolithic interest, but rather from several intertwined interests, even within a short period of time, resulting in their failures to model skip behaviors; (2) long-term: interaction sequences are primarily observed sparsely at discrete intervals, other than consecutively over the long run. This renders difficulty in inferring long-term interests, since only discrete interest representations can be derived, without taking into account interest dynamics across sequences. In this study, we address these concerns by learning (1) multi-scale representations of short-term interests; and (2) dynamics-aware representations of long-term interests. To this end, we present an Interest Dynamics modeling framework using generative Neural Processes, coined IDNP, to model user interests from a functional perspective. IDNP learns a global interest function family to define each user's long-term interest as a function instantiation, manifesting interest dynamics through function continuity. Specifically, IDNP first encodes each user's short-term interactions into multi-scale representations, which are then summarized as user context. By combining latent global interest with user context, IDNP then reconstructs long-term user interest functions and predicts interactions at upcoming query timestep. Moreover, IDNP can model such interest functions even when interaction sequences are limited and non-consecutive. Extensive experiments on four real-world datasets demonstrate that our model outperforms the state-of-the-art on various evaluation metrics.

The session-based recommendation aims to predict users' immediate next actions based on their short-term behaviors reflected by past and ongoing sessions. Graph neural networks (GNNs) recently dominated the related studies, yet their performance heavily relies on graph structures, which are often predefined, task-specific, and designed heuristically. Furthermore, existing graph-based methods either neglect implicit correlations among items or consider explicit and implicit relationships altogether in the same graphs. We propose to decouple explicit and implicit relationships among items. As such, we can capture the prior knowledge encapsulated in explicit dependencies and learned implicit correlations among items simultaneously in a flexible and more interpretable manner for effective recommendations. We design a dual graph neural network that leverages the feature representations extracted by two GNNs: a graph neural network with a single gate (SG-GNN) and an adaptive graph neural network (A-GNN). The former models explicit dependencies among items. The latter employs a self-learning strategy to capture implicit correlations among items. Our experiments on four real-world datasets show our model outperforms state-of-the-art methods by a large margin, achieving 18.46% and 70.72% improvement in [email protected], and 49.10% and 115.29% improvement in [email protected] on Diginetica and LastFM datasets.

Sequential recommendation aims to predict the next item which interests users via modeling their interest in items over time. Most of the existing works on sequential recommendation model users’ dynamic interest in specific items while overlooking users’ static interest revealed by some static attribute information of items, e.g., category, brand. Moreover, existing works often only consider the positive excitation of a user’s historical interactions on his/her next choice on candidate items while ignoring the commonly existing negative excitation, resulting in insufficiently modeling dynamic interest. The overlook of static interest and negative excitation will lead to incomplete interest modeling and thus impedes the recommendation performance. To this end, in this paper, we propose modeling both static interest and negative excitation for dynamic interest to further improve the recommendation performance. Accordingly, we design a novel Static-Dynamic Interest Learning (SDIL) framework featured with a novel Temporal Positive and Negative Excitation Modeling (TPNE) module for accurate sequential recommendation. TPNE is specially designed for comprehensively modeling dynamic interest based on temporal positive and negative excitation learning. Extensive experiments on three real-world datasets show that SDIL can effectively capture both static and dynamic interest and outperforms state-of-the-art baselines.

Within-basket recommendation is to recommend suitable items for the current basket with some already known items. The within-basket auxiliary item recommendation ( WBAIR ) is to recommend auxiliary items based on the primary items in the basket. Such a task exists in many real-life scenarios. Unlike the associations between items that can be transmitted in both directions, primary and auxiliary relationships are unidirectional. Then, the suitable matching patterns between primary and auxiliary items cannot be explored by traditional directionless methods. Therefore, we design the Matc4Rec algorithm to integrate the primary and auxiliary factors, and finally recommend items that not only match the interests of users but also satisfy the primary and auxiliary relationships between items. Specifically, we capture the pattern from three aspects: matchability within-basket , matchability between baskets , and ubiquity . By exploiting this pattern, the designed algorithm not only achieves good results on real-world datasets but also improves the interpretability of recommendations. As a result, we can know which commodities are suitable as auxiliary items. The experiment results demonstrate that our algorithm can also alleviate the cold start problem.

Recent advances in reinforcement learning have inspired increasing interest in learning user modeling adaptively through dynamic interactions, e.g., in reinforcement learning based recommender systems. In most reinforcement learning applications, reward functions provide the critical guideline for optimization. However, current reinforcement learning-based methods rely on manually-defined reward functions, which cannot adapt to dynamic, noisy environments. Moreover, they generally use task-specific reward functions that sacrifice generalization ability. We propose a generative inverse reinforcement learning for user behavioral preference modeling to address the above issues. Instead of using predefined reward functions, our model can automatically learn the rewards from user's actions based on discriminative actor-critic network and Wasserstein GAN. Our model provides a general approach to characterizing and explaining underlying behavioral tendencies. Our experiments show our method outperforms state-of-the-art methods in several scenarios, namely traffic signal control, online recommender systems, and scanpath prediction.

Human activity recognition has become an important challenge yet to resolve while also having promising benefits in various applications for years. Existing approaches have made great progress by applying deep-learning and attention-based methods. However, the deep learning-based approaches may not fully exploit the features to resolve multimodal human activity recognition tasks. Also, the potential of attention-based methods still has not been fully explored to better extract the multimodal spatial-temporal relationship and produce robust results. In this work, we propose Multi-agent Transformer Network (MATN), a multi-agent attention-based deep learning algorithm, to address the above issues in multimodal human activity recognition. We first design a unified representation learning layer to encode the multimodal data, which preprocesses the data in a generalized and efficient way. Then we develop a multimodal spatial-temporal transformer module that applies the attention mechanism to extract the salient spatial-temporal features. Finally, we use a multi-agent training module to collaboratively select the informative modalities and predict the activity labels. We have extensively conducted experiments to evaluate MATN's performance on two public multimodal human activity recognition datasets. The results show that our model has achieved competitive performance compared to the state-of-the-art approaches, which also demonstrates scalability, effectiveness, and robustness.

Pedestrian trajectory prediction is essential for many modern applications, such as abnormal motion analysis and collision avoidance for improved traffic safety. Previous studies still face challenges in embracing high social interaction, dynamics, and multi-modality for achieving high accuracy with long-time predictions. We propose Social Graph Transformer Networks for multi-modal prediction of pedestrian trajectories, where we combine Graph Convolutional Network and Transformer Network by generating stable resolution pseudo-images from Spatio-temporal graphs through a designed stacking and interception method. Specifically, we adopt adjacency matrices to obtain Spatio-temporal features and Transformer for long-time trajectory predictions. As such, we retrain the advantages of both, i.e., the ability to aggregate information over an arbitrary number of neighbors and to conduct complex time-dependent data processing. Our experimental results show that our model reduces the final displacement error and achieves state-of-the-art in multiple metrics. The module's effectiveness is demonstrated through ablation experiments.

Deep reinforcement learning (DRL) has been proven its efficiency in capturing users’ dynamic interests in recent literature. However, training a DRL agent is challenging, because of the sparse environment in recommender systems (RS), DRL agents could spend times either exploring informative user-item interaction trajectories or using existing trajectories for policy learning. It is also known as the exploration and exploitation trade-off which affects the recommendation performance significantly when the environment is sparse. It is more challenging to balance the exploration and exploitation in DRL RS where RS agent need to deeply explore the informative trajectories and exploit them efficiently in the context of recommender systems. As a step to address this issue, We design a novel empowerment-driven exploration method to increase the capability of exploring informative interaction trajectories in the sparse environment, which are further enriched via a counterfactual augmentation strategy for more efficient exploitation. The extensive experiments on four offline datasets and an online simulation platform demonstrate the superiority of our model to a set of existing state-of-the-art methods.

Inferring causal effects on observational data has been widely adopted in various fields. One of the cornerstones of causal inference research, named Individual Treatment Effects (ITE) estimation, aims to predict the expected difference between the treatment and control outcome. It provides a more precise solution to meeting personalized needs while enhancing prediction accuracy in machine learning tasks. Nevertheless, the lack of counterfactual truth and selection bias remain the main challenges in ITE estimation and exert detrimental effects on inference accuracy. In this work, we propose a novel Contrastive Individual Treatment Effects (CITE) estimation framework to alleviate both above issues. Based on the contrastive task designed for causal inference, we fully exploit the self-supervision information hidden in data to achieve balanced and predictive representations while appropriately leveraging causal prior knowledge. Our method outperforms the state-of-the-art ITE estimation algorithms on several real-world and semi-synthetic datasets, which validates its efficacy and superiority.

With the widespread accumulation of observational data, researchers obtain a new direction to learn counterfactual effects in many domains (e.g., health care and computational advertising) without Randomized Controlled Trials (RCTs). However, observational data suffer from inherent missing counterfactual outcomes and distribution discrepancy between treatment and control groups due to behaviour preference. Motivated by recent advances in representation learning in domain adaptation, we propose a novel framework based on Cycle-Balanced REpresentation learning for counterfactual inference (CBRE) to solve the above problems. Specifically, we realize a robust and balanced representation for different groups using adversarial training. Meanwhile, we construct an information loop that preserves original data properties cyclically, reducing information loss when transforming data into latent representation space. Experimental results on three real-world datasets demonstrate that CBRE matches/outperforms the state-of-the-art methods, and it has a great potential to be applied to counterfactual inference.

Online recommendation requires handling rapidly changing user preferences. Deep reinforcement learning (DRL) is an effective means of capturing users' dynamic interest during interactions with recommender systems. Generally, it is challenging to train a DRL agent in online recommender systems because of the sparse rewards caused by the large action space (e.g., candidate item space) and comparatively fewer user interactions. Leveraging experience replay (ER) has been extensively studied to conquer the issue of sparse rewards. However, they adapt poorly to the complex environment of online recommender systems and are inefficient in learning an optimal strategy from past experience. As a step to filling this gap, we propose a novel state-aware experience replay model, in which the agent selectively discovers the most relevant and salient experiences and is guided to find the optimal policy for online recommendations. In particular, a locality-sensitive hashing method is proposed to selectively retain the most meaningful experience at scale and a prioritized reward-driven strategy is designed to replay more valuable experiences with higher chance. We formally show that the proposed method guarantees the upper and lower bound on experience replay and optimizes the space complexity, as well as empirically demonstrate our model's superiority to several existing experience replay methods over three benchmark simulation platforms.

Social recommendation with Graph Neural Networks(GNNs) learns to represent cold users by fusing user-user social relations with user-item interactions, thereby alleviating the cold-start problem associated with recommender systems. Despite being well adapted to social relations and user-item interactions, these supervised models are still susceptible to popularity bias. Contrastive learning helps resolve this dilemma by identifying the properties that distinguish positive from negative samples. In its previous combinations with recommender systems, social relationships and cold-start cases in this context are not considered. Also, they primarily focus on collaborative features between users and items, leaving the similarity between items under-utilized. In this work, we propose socially-aware dual contrastive learning for cold-start recommendation, where cold users can be modeled in the same way as warm users. To take full advantage of social relations, we create dynamic node embeddings for each user by aggregating information from different neighbors according to each different query item, in the form of user-item pairs. We further design a dual-branch self-supervised contrastive objective to account for user-item collaborative features and item-item mutual information, respectively. On one hand, our framework eliminates popularity bias with proper negative sampling in contrastive learning, without extra ground-truth supervision. On the other hand, we extend previous contrastive learning methods to provide a solution to cold-start problem with social relations included. Extensive experiments on two real-world social recommendation datasets demonstrate its effectiveness.

Neural Multi-task Learning is gaining popularity as a way to learn multiple tasks jointly within a single model. While related research continues to break new ground, two major limitations still remain, including (i) poor generalization to scenarios where tasks are loosely correlated; and (ii) under-investigation on global commonality and local characteristics of tasks. Our aim is to bridge these gaps by presenting a neural multi-task learning model coined Hierarchical Task-aware Multi-headed Attention Network (HTMN). HTMN explicitly distinguishes task-specific features from task-shared features to reduce the impact caused by weak correlation between tasks. The proposed method highlights two parts: Multi-level Task-aware Experts Network that identifies task-shared global features and task-specific local features, and Hierarchical Multi-Head Attention Network that hybridizes global and local features to profile more robust and adaptive representations for each task. Afterwards, each task tower receives its hybrid task-adaptive representation to perform task-specific predictions. Extensive experiments on two real datasets show that HTMN consistently outperforms the compared methods on a variety of prediction tasks.

The feature analysis of point clouds, a popular representation of three-dimensional (3D) objects, is rising as a hot research topic nowadays. Point cloud data bear a sparse and unordered nature, making many commonly used feature extraction methods, for example, Convolutional Neural Networks (CNNs) inapplicable, while previous models suitable for the task are usually complex. We aim to reduce model complexity by reducing the number of parameters while achieving better (or at least comparable) performance. We propose an Interpolation Graph Convolutional Network (IGCN) for extracting features of point clouds. IGCN uses the point cloud graph structure and a specially designed Interpolation Convolution Kernel to mimic the operations of CNN for feature extraction. On the basis of weight postfusion and multilevel-resolution aggregation, IGCN not only reduces the cost of calculating the interpolation operation but also improves the model's performance. We validate the performance of IGCN on both point cloud classification and segmentation tasks and explore the contribution of each module of our model through ablation experiments. Furthermore, we embed the IGCN point cloud feature extraction module as a plug-and-play module into other frameworks and perform point cloud registration experiments.

Deep reinforcement learning enables an agent to capture users' interest through dynamic interactions with the environment. It uses a reward function to learn user's interest and to control the learning process, attracting great interest in recommendation research. However, most reward functions are manually designed; they are either too unrealistic or imprecise to reflect the variety, dimensionality, and non-linearity of the recommendation problem. This impedes the agent from learning an optimal policy in highly dynamic online recommendation scenarios. To address the above issue, we propose a generative inverse reinforcement learning approach that avoids the need of defining an elaborative reward function. In particular, we model the recommendation problem as an automatic policy learning problem. We first generate policies based on observed users' preferences and then evaluate the learned policy by a measurement based on a discriminative actor-critic network. We conduct experiments on an online platform, VirtualTB, and demonstrate the feasibility and effectiveness of our proposed approach via comparisons with several state-of-the-art methods.

The ability to deal with uncertainty in machine learning models has become equally, if not more, crucial to their predictive ability itself. For instance, during the pandemic, governmental policies and personal decisions are constantly made around uncertainties. Targeting this, Neural Process Families (NPFs) have recently shone a light on prediction with uncertainties by bridging Gaussian processes and neural networks. Latent neural process, a member of NPF, is believed to be capable of modelling the uncertainty on certain points (local uncertainty) as well as the general function priors (global uncertainties). Nonetheless, some critical questions remain unresolved, such as a formal definition of global uncertainties, the causality behind global uncertainties, and the manipulation of global uncertainties for generative models. Regarding this, we build a member GloBal Convolutional Neural Process(GBCoNP) that achieves the SOTA log-likelihood in latent NPFs. It designs a global uncertainty representation p(z), which is an aggregation on a discretized input space. The causal effect between the degree of global uncertainty and the intra-task diversity is discussed. The learnt prior is analyzed on a variety of scenarios, including 1D, 2D, and a newly proposed spatial-temporal COVID dataset. Our manipulation of the global uncertainty not only achieves generating the desired samples to tackle few-shot learning, but also enables the probability evaluation on the functional priors.

Deep learning frameworks generally require sufficient training data to generalize well while fail to adapt on small or few-shot datasets. Meta-learning offers an effective means of tackling few-shot scenarios and has drawn increasing attention in recent years. Meta-optimization aims to learn a shared set of parameters across tasks for meta-learning while facing challenges in determining whether an initialization condition can be generalized to tasks with diverse distributions. In this regard, we propose a meta-gradient boosting framework that can fit diverse distributions based on a base learner (which learns shared information across tasks) and a series of gradient-boosted modules (which capture task-specific information). We evaluate the model on several few-shot learning benchmarks and demonstrate the effectiveness of our model in modulating task-specific meta-learned priors and handling diverse distributions.

In e-commerce platforms, the online descriptive information of products shows significant impacts on the purchase behaviors. To attract potential buyers for product promotion, numerous workers are employed to write the impressive product descriptions. The hand-crafted product descriptions are less-efficient with great labor costs and huge time consumption. Meanwhile, the generated product descriptions do not take consideration into the customization and the diversity to meet users’ interests. To address these problems, we propose one generic framework, namely DeepDepict, to automatically generate the information-rich and personalized product descriptive information. Specifically, DeepDepict leverages the graph attention to retrieve the product-related knowledge from external knowledge base to enrich the diversity of products, constructs the personalized lexicon to capture the linguistic traits of individuals for the personalization of product descriptions, and utilizes multiple pointer-generator network to fuse heterogeneous data from multi-sources to generate informative and personalized product descriptions. We conduct intensive experiments on one public dataset. The experimental results show that DeepDepict outperforms existing solutions in terms of description diversity, BLEU, and personalized degree with significant margin gain, and is able to generate product descriptions with comprehensive knowledge and personalized linguistic traits.

Most existing recommender systems leverage user behavior data of one type only, such as the purchase behavior in E-commerce that is directly related to the business Key Performance Indicator (KPI) of conversion rate. Besides the key behavioral data, we argue that other forms of user behaviors also provide valuable signal, such as views, clicks, adding a product to shopping carts and so on. They should be taken into account properly to provide quality recommendation for users. In this work, we contribute a new solution named short for Neural Multi-Task Recommendation (NMTR) for learning recommender systems from user multi-behavior data. We develop a neural network model to capture the complicated and multi-type interactions between users and items. In particular, our model accounts for the cascading relationship among different types of behaviors (e.g., a user must click on a product before purchasing it). To fully exploit the signal in the data of multiple types of behaviors, we perform a joint optimization based on the multi-task learning framework, where the optimization on a behavior is treated as a task. Extensive experiments on two real-world datasets demonstrate that NMTR significantly outperforms state-of-the-art recommender systems that are designed to learn from both single-behavior data and multi-behavior data. Further analysis shows that modeling multiple behaviors is particularly useful for providing recommendation for sparse users that have very few interactions.

Accurate demand forecasting of different public transport modes (e.g., buses and light rails) is essential for public service operation. However, the development level of various modes often varies significantly, which makes it hard to predict the demand of the modes with insufficient knowledge and sparse station distribution (i.e., station-sparse mode). Intuitively, different public transit modes may exhibit shared demand patterns temporally and spatially in a city. As such, we propose to enhance the demand prediction of station-sparse modes with the data from station-intensive mode and design a Memory-Augmented Multi-task Re current Network (MATURE) to derive the transferable demand patterns from each mode and boost the prediction of station-sparse modes through adapting the relevant patterns from the station-intensive mode. Specifically, MATURE comprises three components: 1) a memory-augmented recurrent network for strengthening the ability to capture the long-short term information and storing temporal knowledge of each transit mode; 2) a knowledge adaption module to adapt the relevant knowledge from a station-intensive source to station-sparse sources; 3) a multi-task learning framework to incorporate all the information and forecast the demand of multiple modes jointly. The experimental results on a real-world dataset covering four public transport modes demonstrate that our model can promote the demand forecasting performance for the station-sparse modes.

A big challenge existing in genetic functionality prediction is that genetic datasets comprise few samples but massive unclear structured features, i.e., 'large p, small N' problem. To tackle this problem, we propose Non-local Self-attentive Autoencoder (NSAE) which applies attention-driven genetic variant modelling. The backbone attention layer captures long-range dependency relationship among cells (i.e., features) and thus allocates weights to construct attention maps based on cell significance. Utilizing attention maps, NSAE can effectively seize and leverage significant features in a non-local way from numerous cells. Our proposed NSAE outperforms the state-of-the-art algorithms on two genomics datasets from Roadmap projects. The visualization of the attention layer also validates NSAE's ability to highlight important features.

Adversarial examples can be detrimental to a recommender,leading to a surging enthusiasm for applying adversarial learning to improve recommendation performance, e.g. raising model robustness, alleviating data sparsity, generating initial profiles for cold-start users or items, etc. Most existing adversarial example generation methods fall within three categories: attacking the user-item interactions or auxiliary contents, adding perturbations in latent space, sampling the latent space according to certain distribution. In this work, we focus on the semantic-rich user-item interactions in a recommender system and propose a novel generative adversarial network (GAN) named Convolutional Generative Collaborative Filtering (Conv-GCF). We develop an effective perturbation mechanism (adversarial noise layer) for convolutional neural networks (CNN), based on which we design a generator with residual blocks to synthesize user-item interactions. We empirically demonstrate that on Conv-GCF, the adversarial noise layer is superior to the conventional noise-adding approach. Moreover, we propose two types of discriminators: one using Bayes Personalized Ranking (BPR) and the other with binary classification. On four public datasets, we show that our approach achieves the state-of-the-art top-n recommendation performance among competitive baselines.

A common challenge for most current recommender systems is the cold-start problem. Due to the lack of user-item interactions, the fine-tuned recommender systems are unable to handle situations with new users or new items. Recently, some works introduce the meta-optimization idea into the recommendation scenarios, i.e. predicting the user preference by only a few of past interacted items. The core idea is learning a global sharing initialization parameter for all users and then learning the local parameters for each user separately. However, most meta-learning based recommendation approaches adopt model-agnostic meta-learning for parameter initialization, where the global sharing parameter may lead the model into local optima for some users. In this paper, we design two memory matrices that can store task-specific memories and feature-specific memories. Specifically, the feature-specific memories are used to guide the model with personalized parameter initialization, while the task-specific memories are used to guide the model fast predicting the user preference. And we adopt a meta-optimization approach for optimizing the proposed method. We test the model on two widely used recommendation datasets and consider four cold-start situations. The experimental results show the effectiveness of the proposed methods.

The flourishing of social media platforms requires techniques for understanding the content of media on a large scale. However, state-of-the art video event understanding approaches remain very limited in terms of their ability to deal with data sparsity, semantically unrepresentative event names, and lack of coherence between visual and textual concepts. Accordingly, in this paper, we propose a method of grounding visual concepts for large-scale Multimedia Event Detection (MED) and Multimedia Event Captioning (MEC) in zero-shot setting. More specifically, our framework composes the following: (1) deriving the novel semantic representations of events from their textual descriptions, rather than event names; (2) aggregating the ranks of grounded concepts for MED tasks. A statistical mean-shift outlier rejection model is proposed to remove the outlying concepts which are incorrectly grounded; and (3) defining MEC tasks and augmenting the MEC training set by the videos detected in MED in a zero-shot setting. To the best of our knowledge, this work is the first time to define and solve the MEC task, which is a further step towards understanding video events. We conduct extensive experiments and achieve state-of-the-art performance on the TRECVID MEDTest dataset, as well as our newly proposed TRECVID-MEC dataset.

It has been a significant challenge to portray intraclass disparity precisely in the area of activity recognition, as it requires a robust representation of the correlation between subject-specific variation for each activity class. In this work, we propose a novel end-to-end knowledge directed adversarial learning framework, which portrays the class-conditioned intraclass disparity using two competitive encoding distributions and learns the purified latent codes by denoising learned disparity. Furthermore, the domain knowledge is incorporated in an unsupervised manner to guide the optimization and further boosts the performance. The experiments on four HAR benchmark datasets demonstrate the robustness and generalization of our proposed methods over a set of state-of-the-art. We further prove the effectiveness of automatic domain knowledge incorporation in performance enhancement.

Human Activity Recognition (HAR) plays an irreplaceable role in various applications such as security, gaming, and assisted living. Recent studies introduce deep learning to mitigate the manual feature extraction (i.e., data representation) efforts and achieve high accuracy. However, there are still challenges in learning accurate representations for sensory data due to the weakness of representation modules and the subject variances. We propose a scheme called Distance-based HAR from Ensembled spatial-temporal Representations (DHARER) to address above challenges. The idea behind DHARER is straightforward—the same activities should have similar representations. We first learn representations of the input sensory segments and latent prototype representations of each class, using a Convolution Neural Network (CNN)-based dual-stream representation module; then the learned representations are projected to activity types by measuring their similarity to the learned prototypes. We have conducted extensive experiments under a strict subject-independent setting on three large-scale datasets to evaluate the proposed scheme, and our experimental results demonstrate superior performance of DHARER to several state-of-the-art methods.

Adversarial attacks pose significant challenges for detecting adversarial attacks at an early stage. We propose attack-agnostic detection on reinforcement learning-based interactive recommendation systems. We first craft adversarial examples to show their diverse distributions and then augment recommendation systems by detecting potential attacks with a deep learning-based classifier based on the crafted data. Finally, we study the attack strength and frequency of adversarial examples and evaluate our model on standard datasets with multiple crafting methods. Our extensive experiments show that most adversarial attacks are effective, and both attack strength and attack frequency impact the attack performance. The strategically-timed attack achieves comparative attack performance with only 1/3 to 1/2 attack frequency. Besides, our black-box detector trained with one crafting method has the generalization ability over several crafting methods.

Biometric authentication involves various technologies to identify individuals by exploiting their unique, measurable physiological and behavioral characteristics. However, traditional biometric authentication systems (e.g., face recognition, iris, retina, voice, and fingerprint) are at increasing risks of being tricked by biometric tools such as anti-surveillance masks, contact lenses, vocoder, or fingerprint films. In this article, we design a multimodal biometric authentication system named DeepKey, which uses both Electroencephalography (EEG) and gait signals to better protect against such risk. DeepKey consists of two key components: an Invalid ID Filter Model to block unauthorized subjects, and an identification model based on attention-based Recurrent Neural Network (RNN) to identify a subject’s EEG IDs and gait IDs in parallel. The subject can only be granted access while all the components produce consistent affirmations to match the user’s proclaimed identity. We implement DeepKey with a live deployment in our university and conduct extensive empirical experiments to study its technical feasibility in practice. DeepKey achieves the False Acceptance Rate (FAR) and the False Rejection Rate (FRR) of 0 and 1.0%, respectively. The preliminary results demonstrate that DeepKey is feasible, shows consistent superior performance compared to a set of methods, and has the potential to be applied to the authentication deployment in real-world settings.

Online ride-sharing platforms have become a critical part of the urban transportation system. Accurately recommending hotspots to drivers in such platforms is essential to help drivers find passengers and improve users' experience, which calls for efficient passenger demand prediction strategy. However, predicting multi-step passenger demand is challenging due to its high dynamicity, complex dependencies along spatial and temporal dimensions, and sensitivity to external factors (meteorological data and time meta). We propose an end-to-end deep learning framework to address the above problems. Our model comprises three components in pipeline: 1) a cascade graph convolutional recurrent neural network to accurately extract the spatial-temporal correlations within citywide historical passenger demand data; 2) two multi-layer LSTM networks to represent the external meteorological data and time meta, respectively; 3) an encoder-decoder module to fuse the above two parts and decode the representation to predict over multi-steps into the future. The experimental results on three real-world datasets demonstrate that our model can achieve accurate prediction and outperform the most discriminative state-of-the-art methods.

Knowledge graph (KG) embedding techniques represent entities and relations as low-dimensional, continuous vectors, and thus enables machine learning models to be easily adapted to KG completion and querying tasks. However, learned dense vectors are inefficient for large-scale similarity computations. Learning-to-hash is to learn compact binary codes from high-dimensional input data and provides a promising way to accelerate efficiency by measuring Hamming distance instead of Euclidean distance or dot-product. Unfortunately, most of learning-to-hash methods cannot be directly applied to KG structure encoding. In this paper, we introduce a novel framework for encoding incomplete KGs and graph queries in Hamming space. To preserve KG structure information from embeddings to hash codes and address the ill-posed gradient issue in optimization, we utilize a continuation method with convergence guarantees to jointly encode queries and KG entities with geometric operations. The hashed embedding of a query can be utilized to discover target answers from incomplete KGs whilst the efficiency has been greatly improved.We compared our model with state-of-the-art methods on real-world KGs. Experimental results show that our framework not only significantly speeds up the searching process, but also provides good results for unanswerable queries caused by incomplete information.

As brain dynamics fluctuate considerably across different subjects, it is challenging to design effective handcrafted features based on prior knowledge. Regarding this gap, this paper proposes a Graph-based Convolutional Recurrent Attention Model (G-CRAM) to explore EEG features across different subjects for movement intention recognition. A graph structure is first developed to embed the positioning information of EEG nodes, and then a convolutional recurrent attention model learns EEG features from both spatial and temporal dimensions and adaptively emphasizes on the most distinguishable temporal periods. The proposed approach is validated on two public movement intention EEG datasets. The results show that the GCRAM achieves superior performance to state-of-the-art methods regarding recognition accuracy and ROC-AUC. Furthermore, model interpreting studies reveal the learning process of different neural network components and demonstrate that the proposed model can extract detailed features efficiently.

Electroencephalography (EEG) signals reflect and measure activities in certain brain areas. Its zero clinical risk and easy-to-use features make it a good choice of providing insights into the cognitive process. However, effective analysis of time-varying EEG signals remains challenging. First, EEG signal processing and feature engineering are time-consuming and highly rely on expert knowledge, and most existing studies focus on domain-specific classification algorithms, which may not apply to other domains. Second, EEG signals usually have low signal-to-noise ratios and are more chaotic than other sensor signals. In this regard, we propose a generic EEG-based cognitive activity recognition framework that can adaptively support a wide range of cognitive applications to address the above issues. The framework uses a reinforced selective attention model to choose the characteristic information among raw EEG signals automatically. It employs a convolutional mapping operation to dynamically transform the selected information into a feature space to uncover the implicit spatial dependency of EEG sample distribution. We demonstrate the effectiveness of the framework under three representative scenarios: intention recognition with motor imagery EEG, person identification, and neurological diagnosis, and further evaluate it on three widely used public datasets. The experimental results show our framework outperforms multiple state-of-the-art baselines and achieves competitive accuracy on all the datasets while achieving low latency and high resilience in handling complex EEG signals across various domains. The results confirm the suitability of the proposed generic approach for a range of problems in the realm of brain-computer Interface applications.

Sharing ubiquitous mobile sensor data, especially physiological data, raises potential risks of leaking physical and demographic information that can be inferred from the time series sensor data. Existing sensitive information protection mechanisms that depend on data transformation are effective only on a particular sensitive attribute, together with usually requiring the labels of sensitive information for training. Considering this gap, we propose a novel user sensitive information protection framework without using a sensitive training dataset or being validated on protecting only one specific sensitive information. The presented approach transforms raw sensor data into a new format that has a "style" (sensitive information) of random noise and a "content" (desired information) of the raw sensor data, thus is free of user sensitive information for training and able to collectively protect all sensitive information at once. Our implementation and experiments on two real-world multisensor human activity datasets demonstrate that the proposed data transformation technique can achieve the protection for all sensitive information at once without requiring the knowledge of users' personal attributes for training, and simultaneously preserve the usability of the new transformed data with regard to inferring human activities with insignificant performance loss.

Semi-supervised learning is sought for leveraging the unlabelled data when labelled data is difficult or expensive to acquire. Deep generative models (e.g., Variational Autoencoder (VAE)) and semi-supervised Generative Adversarial Networks (GANs) have recently shown promising performance in semi-supervised classification for the excellent discriminative representing ability. However, the latent code learned by the traditional VAE is not exclusive (repeatable) for a specific input sample, which prevents it from excellent classification performance. In particular, the learned latent representation depends on a non-exclusive component which is stochastically sampled from the prior distribution. Moreover, the semi-supervised GAN models generate data from pre-defined distribution (e.g., Gaussian noises) which is independent of the input data distribution and may obstruct the convergence and is difficult to control the distribution of the generated data. To address the aforementioned issues, we propose a novel Adversarial Variational Embedding (AVAE) framework for robust and effective semi-supervised learning to leverage both the advantage of GAN as a high quality generative model and VAE as a posterior distribution learner. The proposed approach first produces an exclusive latent code by the model which we call VAE++, and meanwhile, provides a meaningful prior distribution for the generator of GAN. The proposed approach is evaluated over four different real-world applications and we show that our method outperforms the state-of-the-art models, which confirms that the combination of VAE++ and GAN can provide significant improvements in semi-supervised lassification.

Most of recent neural network(NN)-based recommendation techniques mainly focus on improving the overall performance, such as hit ratio for top-N recommendation, where the users' feedbacks are considered as the ground-truth. In real-world applications, those feedbacks are possibly contaminated by imperfect user behaviours, posing challenges on the design of robust recommendation methods. Some methods apply man-made noises on the input data to train the networks more effectively (e.g. the collaborative denoising auto-encoder). In this work, we propose a general adversarial training framework for NN-based recommendation models, improving both the model robustness and the overall performance. We apply our approach on the collaborative auto-encoder model, and show that the combination of adversarial training and NN-based models outperforms highly competitive state-of-the-art recommendation methods on three public datasets.

Brain-Computer Interface (BCI) enables human to communicate with and intuitively control an external device through brain signals. Movement intention recognition paves the path for developing BCI applications. The current state-of-the-art in EEG based BCI usually involves subject-specific adaptation before ready to use. However, the subject-independent scenario, in which a well-trained model is directly applied to new subjects without any pre-calibration, is particularly desired yet rarely explored. In order to fill the gap, we present a Convolutional Attention Model (CAM) for EEG-based human movement intention recognition in the subject-independent scenario. The convolutional network is designed to capture the spatio-temporal features of EEG signals, while the integrated attention mechanism is utilized to focus on the most discriminative information of EEG signals during the period of movement imagination while omitting other less relative parts. Experiments conducted on a real-world EEG dataset containing 55 subjects show that our model is capable of mining the underlying invariant EEG patterns across different subjects and generalizing to unseen subjects. Our model achieves better performance than a series of state-of-the-art and baseline approaches.

Most of the existing analytics on ICU data mainly focus on mortality risk prediction and phenotyping analysis. However, they have limitations in providing sufficient evidence for decision making in a dynamically changing clinical environment. In this paper, we propose a novel approach that simultaneously analyses different organ systems to predict the illness severity of patients in an ICU, which can intuitively reflect the condition of the patients in a timely fashion. Specifically, we develop a novel deep learning model, namely MTRNN-ATT, which is based on multi-task recurrent neural networks. The physiological features of each organ system in time-series representations are learned by a single long short-term memory unit as a specific task. To utilize the relationships between organ systems, we use a shared LSTM unit to exploit the correlations between different tasks for further performance improvement. Also, we apply an attention mechanism in our deep model to learn the selective features at each stage to achieve better prediction results. We conduct extensive experiments on a real-world clinical dataset (MIMIC-III) to compare our method with many state-of-the-art methods. The experiment results demonstrate that the proposed approach performs better on the prediction tasks of illness severity scores.

Recognition of human intention based on Electroencephalography (EEG) signals attracts strong research interest in pattern recognition because of its promising applications that enable non-muscular communications and controls. Over the past few years, most EEG-based recognition works make significant efforts to learn extracted features to explore specific patterns between a segment of EEG signals and the corresponding activities. Unfortunately, vectorization-based feature representations, either vector-like or matrix-like ones, suffer from massive signal noise and difficulties of exploiting signal correlations between adjacent sensors of EEG signals. Most importantly, EEG signals are represented by one unique frequency and then fed into the subsequent learning model. Neglecting different frequencies of EEG signals can be detrimental to activity recognition because a particular frequency of EEG signals is more helpful to recognize some activities. Inspired by this idea, we propose to extract EEG signals with different frequencies and introduce a novel Multi-task deep learning model to learn the human intentions. We have conducted extensive experiments on a publicly available EEG benchmark dataset and compared our method with many state-of-the-art algorithms. The experimental results demonstrate that the proposed Multi-task deep recurrent neural network outperforms all the compared methods in a multi-class scenario.

Collaborative filtering (CF) has been successfully used to provide users with personalized products and services. However, dealing with the increasing sparseness of user-item matrix still remains a challenge. To tackle such issue, hybrid CF such as combining with content based filtering and leveraging side information of users and items has been extensively studied to enhance performance. However, most of these approaches depend on hand-crafted feature engineering, which is usually noise-prone and biased by different feature extraction and selection schemes. In this paper, we propose a new hybrid model by generalizing contractive auto-encoder paradigm into matrix factorization framework with good scalability and computational efficiency, which jointly models content information as representations of effectiveness and compactness, and leverage implicit user feedback to make accurate recommendations. Extensive experiments conducted over three large-scale real datasets indicate the proposed approach outperforms the compared methods for item recommendation.

With recent advances in radio-frequency identification (RFID), wireless sensor networks, and Web services, physical things are becoming an integral part of the emerging ubiquitous Web. Finding correlations among ubiquitous things is a crucial prerequisite for many important applications such as things search, discovery, classification, recommendation, and composition. This article presents DisCor-T , a novel graph-based approach for discovering underlying connections of things via mining the rich content embodied in the human-thing interactions in terms of user, temporal, and spatial information. We model this various information using two graphs, namely a spatio-temporal graph and a social graph. Then, random walk with restart (RWR) is applied to find proximities among things, and a relational graph of things (RGT) indicating implicit correlations of things is learned. The correlation analysis lays a solid foundation contributing to improved effectiveness in things management and analytics. To demonstrate the utility of the proposed approach, we develop a flexible feature-based classification framework on top of RGT and perform a systematic case study. Our evaluation exhibits the strength and feasibility of the proposed approach.

In the era of big data, a mechanism that can automatically annotate disease codes to patients’ records in the medical information system is in demand. The purpose of this work is to propose a framework that automatically annotates the disease labels of multi-source patient data in Intensive Care Units (ICUs). We extract features from two main sources, medical charts and notes. The Bag-of-Words model is used to encode the features. Unlike most of the existing multi-label learning algorithms that globally consider correlations between diseases, our model learns disease correlation locally in the patient data. To achieve this, we derive a local disease correlation representation to enrich the discriminant power of each patient data. This representation is embedded into a unified multi-label learning framework. We develop an alternating algorithm to iteratively optimize the objective function. Extensive experiments have been conducted on a real-world ICU database. We have compared our algorithm with representative multi-label learning algorithms. Evaluation results have shown that our proposed method has state-of-the-art performance in the annotation of multiple diagnostic codes for ICU patients. This study suggests that problems in the automated diagnosis code annotation can be reliably addressed by using a multi-label learning model that exploits disease correlation. The findings of this study will greatly benefit health care and management in ICU considering that the automated diagnosis code annotation can significantly improve the quality and management of health care for both patients and caregivers.

Data veracity is a grand challenge for various tasks on the Web. Since the web data sources are inherently unreliable and may provide conflicting information about the same real-world entities, truth discovery is emerging as a countermeasure of resolving the conflicts by discovering the truth, which conforms to the reality, from the multi-source data. A major challenge related to truth discovery is that different data items may have varying numbers of true values (or multi-truth), which counters the assumption of existing truth discovery methods that each data item should have exactly one true value. In this paper, we address this challenge by exploiting and leveraging the implications from multi-source data. In particular, we exploit three types of implications, namely the implicit negative claims, the distribution of positive/negative claims, and the co-occurrence of values in sources' claims, to facilitate multi-truth discovery. We propose a probabilistic approach with improvement measures that incorporate the three implications in all stages of truth discovery process. In particular, incorporating the negative claims enables multi-truth discovery, considering the distribution of positive/negative claims relieves truth discovery from the impact of sources' behavioral features in the specific datasets, and considering values' co-occurrence relationship compensates the information lost from evaluating each value in the same claims individually. Experimental results on three real-world datasets demonstrate the effectiveness of our approach.

Truth discovery is the problem of detecting true values from the conflicting data provided by multiple sources on the same data items. Since sources' reliability is unknown a priori, a truth discovery method usually estimates sources' reliability along with the truth discovery process. A major limitation of existing truth discovery methods is that they commonly assume exactly one true value on each data item and therefore cannot deal with the more general case that a data item may have multiple true values (or multi-truth). Since the number of true values may vary from data item to data item, this requires truth discovery methods being able to detect varying numbers of truth values from the multi-source data. In this paper, we propose a multi-truth discovery approach, which addresses the above challenges by providing a generic framework for enhancing existing truth discovery methods. In particular, we redeem the numbers of true values as an important clue for facilitating multi-truth discovery. We present the procedure and components of our approach, and propose three models, namely the byproduct model, the joint model, and the synthesis model to implement our approach. We further propose two extensions to enhance our approach, by leveraging the implications of similar numerical values and values' co-occurrence information in sources' claims to improve the truth discovery accuracy. Experimental studies on real-world datasets demonstrate the effectiveness of our approach.

Orthogonal Non-negative Matrix Factorization (ONMF) approximates a data matrix X by the product of two lower dimensional factor matrices: X -- UVT, with one of them orthogonal. ONMF has been widely applied for clustering, but it often suffers from high computational cost due to the orthogonality constraint. In this paper, we propose a method, called Nonlinear Riemannian Conjugate Gradient ONMF (NRCG-ONMF), which updates U and V alternatively and preserves the orthogonality of U while achieving fast convergence speed. Specifically, in order to update U, we develop a Nonlinear Riemannian Conjugate Gradient (NRCG) method on the Stiefel manifold using Barzilai-Borwein (BB) step size. For updating V, we use a closed-form solution under non-negativity constraint. Extensive experiments on both synthetic and real-world data sets show consistent superiority of our method over other approaches in terms of orthogonality preservation, convergence speed and clustering performance.

With the latest developments in database technologies, it becomes easier to store the medical records of hospital patients from their first day of admission than was previously possible. In Intensive Care Units (ICU), modern medical information systems can record patient events in relational databases every second. Knowledge mining from these huge volumes of medical data is beneficial to both caregivers and patients. Given a set of electronic patient records, a system that effectively assigns the disease labels can facilitate medical database management and also benefit other researchers, e.g., pathologists. In this paper, we have proposed a framework to achieve that goal. Medical chart and note data of a patient are used to extract distinctive features. To encode patient features, we apply a Bag-of-Words encoding method for both chart and note data. We also propose a model that takes into account both global information and local correlations between diseases. Correlated diseases are characterized by a graph structure that is embedded in our sparsity-based framework. Our algorithm captures the disease relevance when labeling disease codes rather than making individual decision with respect to a specific disease. At the same time, the global optimal values are guaranteed by our proposed convex objective function. Extensive experiments have been conducted on a real-world large-scale ICU database. The evaluation results demonstrate that our method improves multi-label classification results by successfully incorporating disease correlations.

Many real-world applications rely on multiple data sources to provide information on their interested items. Due to the noises and uncertainty in data, given a specific item, the information from different sources may conflict. To make reliable decisions based on these data, it is important to identify the trustworthy information by resolving these conflicts, i.e., the truth discovery problem. Current solutions to this problem detect the veracity of each value jointly with the reliability of each source for each data item. In this way, the efficiency of truth discovery is strictly confined by the problem scale, which in turn limits truth discovery algorithms from being applicable on a large scale. To address this issue, we propose an approximate truth discovery approach, which divides sources and values into groups according to a user-specified approximation criterion. The groups are then used for efficient inter-value influence computation to improve the accuracy. Our approach is applicable to most existing truth discovery algorithms. Experiments on real-world datasets show that our approach improves the efficiency compared to existing algorithms while achieving similar or even better accuracy. The scalability is further demonstrated by experiments on large synthetic datasets.

Truth-finding is the fundamental technique for corroborating reports from multiple sources in both data integration and collective intelligent applications. Traditional truth-finding methods assume a single true value for each data item and therefore cannot deal will multiple true values (i.e., the multi-truth-finding problem). So far, the existing approaches handle the multi-truth-finding problem in the same way as the single-truth-finding problems. Unfortunately, the multi-truth-finding problem has its unique features, such as the involvement of sets of values in claims, different implications of inter-value mutual exclusion, and larger source profiles. Considering these features could provide new opportunities for obtaining more accurate truth-finding results. Based on this insight, we propose an integrated Bayesian approach to the multi-truth-finding problem, by taking these features into account. To improve the truth-finding efficiency, we reformulate the multi-truth-finding problem model based on the mappings between sources and (sets of) values. New mutual exclusive relations are defined to reflect the possible co-existence of multiple true values. A finer-grained copy detection method is also proposed to deal with sources with large profiles. The experimental results on three real-world datasets show the effectiveness of our approach.

Understanding and recognizing the activities performed by people is a fundamental research topic for a wide range of important applications such as fall detection of elderly people. In this paper, we present the technical details behind Freedom, a low-cost, unobtrusive system that supports independent livingof the older people. The Freedom system interprets what aperson is doing by leveraging machine learning algorithmsand radio-frequency identification (RFID) technology. To dealwith noisy, streaming, unstable RFID signals, we particularlydevelop a dictionary-based approach that can learn dictionariesfor activities using an unsupervised sparse coding algorithm. Our approach achieves efficient and robust activity recognitionvia a more compact representation of the activities. Extensiveexperiments conducted in a real-life residential environmentdemonstrate that our proposed system offers a good overallperformance (e.g., achieving over 96% accuracy in recognizing23 activities) and has the potential to be further developed tosupport the independent living of elderly people.

Point-of-Interest (POI) recommendation is a new type of recommendation task that comes along with the prevalence of location-based social networks in recent years. Compared with traditional tasks, it focuses more on personalized, context-aware recommendation results to provide better user experience. To address this new challenge, we propose a Collaborative Filtering method based on Non-negative Tensor Factorization, a generalization of the Matrix Factorization approach that exploits a high-order tensor instead of traditional User-Location matrix to model multi-dimensional contextual information. The factorization of this tensor leads to a compact model of the data which is specially suitable for context-aware POI recommendations. In addition, we fuse users' social relations as regularization terms of the factorization to improve the recommendation accuracy. Experimental results on real-world datasets demonstrate the effectiveness of our approach.

RFID-based localization and tracking has some promising potentials. By combining localization with its identification capability, existing applications can be enhanced and new applications can be developed. In this paper, we investigate a tag-free indoor localizing and tracking problem (e.g., people tracking) without requiring subjects to carry any tags or devices in a pure passive environment. We formulate localization as a classification task. In particular, we model the received signal strength indicator (RSSI) of passive tags using multivariate Gaussian Mixture Model (GMM), and use the Expectation Maximization (EM) to learn the maximum likelihood estimates of the model parameters. Several other learning-based probabilistic approaches are also explored in the localization problem. To track a moving subject, we propose GMM based Hidden Markov Model (HMM) and k Nearest Neighbor (kNN) based HMM approaches. We conduct extensive experiments in a testbed formed by passive RFID tags, and the experimental results demonstrate the effectiveness and accuracy of our approach.

Internet of Things (IoT) is an emerging paradigm where physical objects are connected and communicated over the Web. Its capability in assimilating the virtual world and the physical one offers many exciting opportunities. However, how to realize a smooth, seamless integration of the two worlds remains an interesting and challenging topic. In this paper, we showcase an IoT prototype system that enables seamless integration of the virtual and the physical worlds and efficient management of things of interest (TOIs), where services and resources offered by things can be easily monitored, visualized, and aggregated for value-added services by users. This paper presents the motivation, system design, implementation, and demonstration scenario of the system.

Finding relevant Web services and composing them into value-added applications is becoming increasingly important in cloud and service based marketplaces. The key problem with current approaches to finding relevant Web services is that most of them only provide searches over a discrete set of features using exact keyword matching. We demonstrate in this paper that by utilizing well known indexing scheme such as inverted file and R-tree indexes over Web services attributes, the Earth Mover's Distance (EMD) algorithm can be used efficiently to find partial matches between a query and a database of Web services.

With recent advances in radio-frequency identification (RFID), wireless sensor networks, and Web-based services, physical things are becoming an integral part of the emerging ubiquitous Web. In this paper, we focus on the things recommendation problem in Internet of Things (IoT). In particular, we propose a unified probabilistic based framework by fusing information across relationships between users (i.e., users'social network) and things (i.e., things correlations) to make more accurate recommendations. The proposed approach not only inherits the advantages of the matrix factorization, but also exploits the merits of social relationships and thing-thing correlations. We validate our approach based on an Internet of Things platform and the experimental results demonstrate its feasibility and effectiveness.

With recent advances in radio-frequency identification (RFID), wireless sensor networks, and Web services, physical things are becoming an integral part of the emerging ubiquitous Web. Correlation discovery for ubiquitous things is critical for many important applications such as things search, recommendation, annotation, classification, clustering, composition, and management. In this paper, we propose a novel approach for discovering things correlation based on user, temporal, and spatial information captured from usage events of things. In particular, we use a spatio-temporal graph and a social graph to model things usage contextual information and user-thing relationships respectively. Then, we apply random walks with restart on these graphs to compute correlations among things. This correlation analysis lays a solid foundation and contributes to improved effectiveness in things management. To demonstrate the utility of our approach, we perform a systematic case study and comprehensive experiments on things annotation.

With recent advances in radio-frequency identification (RFID), wireless sensor networks, and Web services, physical things are becoming an integral part of the emerging ubiquitous Web. While this integration offers many exciting opportunities such as efficient supply chains and improved environmental monitoring, it also presents many significant challenges. One such challenge lies in how to classify, discover, and manage ubiquitous things, which is critical for efficient and effective object search, recommendation, and composition. In this paper, we focus on automatically classifying ubiquitous things into manageable semantic category labels by exploiting the information hidden in interactions between users and ubiquitous things. We develop a novel approach to extract latent relevance by building a relational network of ubiquitous things (RNUbiT) where similar things are linked via virtual edges according to their latent relevance. A discriminative learning algorithm is also developed to automatically determine category labels for ubiquitous things. We conducted experiments using real-world data and the experimental results demonstrate the feasibility and validity of our proposed approach.

This paper studies web object classification problem with the novel exploration of social tags. More and more web objects are increasingly annotated with human interpretable labels (i.e., tags), which can be considered as an auxiliary attribute to assist the object classification. Automatically classifying web objects into manageable semantic categories has long been a fundamental pre-process for indexing, browsing, searching, and mining heterogeneous web objects. However, such heterogeneous web objects often suffer from a lack of easy-extractable and uniform descriptive features. In this paper, we propose a discriminative tag-centric model for web object classification by jointly modeling the objects category labels and their corresponding social tags and un-coding the relevance among social tags. Our approach is based on recent techniques for learning large-scale discriminative models. We conduct experiments to validate our approach using real-life data. The results show the feasibility and good performance of our approach.

The ability to track and trace individual items, especially through large-scale and distributed networks, is the key to realizing many important business applications such as supply chain management, asset tracking, and counterfeit detection. Unfortunately, enabling traceability across independent organizations still poses significant challenges in dealing with large volume of data and sovereignty of the participants. This paper describes PeerTrack, a scalable platform for efficiently and effectively tracking and tracing objects in large-scale traceability networks. With a novel data model, a DHT-based indexer, and a distributed query processor, PeerTrack provides an environment where traceability applications can share data across independent organizations in a peer-to-peer fashion. This paper presents the motivation, system design, implementation, and a proof-of-concept system of the PeerTrack platform.