WWW 2025 Papers

Large language models (LLM) achieve superior performance in generative tasks. However, due to the natural gap between language model generation and structured information extraction in three dimensions: task type, output format, and modeling granularity, they often fall short in structured information extraction, a crucial capability for effective data utilization on the web. In this paper, we define the generation process of the language model as the controllable state transition, aligning the generation and extraction processes to ensure the integrity of the output structure and adapt to the goals of the information extraction task. Furthermore, we propose the Structure2Text decider to help the language model understand the fine-grained extraction information, which converts the structured output into natural language and makes state decisions, thereby focusing on the task-specific information kernels, and alleviating language model hallucinations and incorrect content generation. We conduct extensive experiments and detailed analyses on myriad information extraction tasks. Our method not only achieves significant performance improvements but also ensures the integrity of the output structure, making it easy to parse the extracted content.

Multi-modal recommender systems (MMRecs) leverage diverse modalities to deliver personalized recommendations, yet they often struggle with efficiency due to the large size of modality encoders and the complexity of fusing high-dimensional features. To address the efficiency issue, a promising solution is to compress a cumbersome MMRec into a lightweight ID-based Multi-Layer Perceptron-based Recommender system (MLPRec) through Knowledge Distillation (KD). Despite effectiveness, this approach overlooks the significant gap between the complex teacher MMRec and the lightweight, ID-based student MLPRec, which differ significantly in size, architecture, and input modalities, leading to ineffective knowledge transfer and suboptimal student performance. To bridge this gap, we propose TARec, a novel teacher-assisted Wasserstein Knowledge Distillation framework for compressing MMRecs into an efficient MLPRec. TARec introduces: (i) a two-staged KD process using an intermediate Teacher Assistant (TA) model to bridge the gap between teacher and student, facilitating smoother knowledge transfer; (ii) logit-level KD using the Wasserstein Distance as metric, replacing the conventional KL divergence to ensure stable gradient flow even with significant teacher-student gaps; and (iii) embedding-level contrastive KD to further distill high-quality embedding-level knowledge from teacher. Extensive experiments on real-world datasets verify the effectiveness of TARec, demonstrating that TARec significantly outperforms the state-of-the-art MMRecs while reducing computational costs. Our anonymous code is available at: https://anonymous.4open.science/r/TARec-0980/.

Dynamics modeling has been introduced as a novel paradigm in message passing (MP) of graph neural networks (GNNs). Existing methods consider MP between nodes as a heat diffusion process, and leverage \textit{heat equation} to model the temporal evolution of nodes in the embedding space. However, heat equation can hardly depict the wave nature of graph signals in graph signal processing. Besides, heat equation is essentially a partial differential equation (PDE) involving a first partial derivative of time, whose numerical solution usually has low stability, and leads to inefficient model training. In this paper, we would like to depict more wave details in MP, since graph signals are essentially wave signals that can be seen as a superposition of a series of waves in the form of eigenvector. This motivates us to consider MP as a wave propagation process to capture the temporal evolution of wave signals in the space. Based on wave equation in physics, we innovatively develop a graph wave equation to leverage the wave propagation on graphs. In details, we demonstrate that the graph wave equation can be connected to traditional spectral GNNs, facilitating the design of graph wave networks (GWNs) based on various Laplacians and enhancing the performance of the spectral GNNs. Besides, the graph wave equation is particularly a PDE involving a second partial derivative of time, which has stronger stability on graphs than the heat equation that involves a first partial derivative of time. Additionally, we theoretically prove that the numerical solution derived from the graph wave equation are constantly stable, enabling to significantly enhance model efficiency while ensuring its performance. Extensive experiments show that GWNs achieve state-of-the-art and efficient performance on benchmark datasets, and exhibit outstanding performance in addressing challenging graph problems, such as over-smoothing and heterophily. Our code is available at https://anonymous.4open.science/r/GWN/.

In digital education, Cognitive Diagnosis (CD) is essential for modeling learners' cognitive states, such as problem-solving ability and knowledge proficiency, by analyzing their response data, like answer correctness. However, traditional CD methods struggle with \textit{effectiveness} and \textit{efficiency}. They fail to capture the diversity and uncertainty of learners' cognitive states. Additionally, response prediction can be time-consuming. To address these issues, we propose BoxCD, a contrastive probabilistic box embedding model for cognitive diagnosis. BoxCD utilizes high-dimensional axis-aligned hyper-rectangles (boxes) to represent learners and exercises, with the volume of intersecting boxes used to predict learners' responses. This approach effectively captures semantic diversity and uncertainty while enhancing diagnostic effectiveness. To stabilize box embeddings, we integrate contrastive learning objectives with response prediction goals, optimizing the distance between positive and negative samples of learner and exercise boxes to improve uniformity. Additionally, we develop a rank-based response prediction method that leverages the geometric properties of box embeddings to efficiently assess learners' response correctness. Comprehensive experiments on two real-world datasets demonstrate that BoxCD outperforms traditional CD models in both effectiveness and efficiency, showcasing its potential to enhance personalized learning in digital education platforms.

Deep learning-based (DL-based) malicious traffic detection methods are effective but vulnerable to adversarial attacks. Existing adversarial attack methods have shown promising results when targeting traffic detection models based on statistics and sequence features. However, these methods are less effective against models that rely on payload analysis. The main reason is the difficulty in generating semantic, compliant, and functional payloads, which limits their practical application. In this paper, we propose AdvTG, an adversarial traffic generation framework based on the large language model (LLM) and reinforcement learning (RL). Specifically, AdvTG is designed to attack various DL-based detection models across diverse features and architectures, thereby enhancing the generalization capabilities of the generated adversarial traffic. Moreover, we design a specialized prompt for payload generation tasks, where functional fields and target types are supplied as input, while non-functional fields are generated to produce the mutated traffic. This fine-tuning endows the LLM with task comprehension and traffic pattern reasoning abilities, allowing it to generate traffic that remains compliant and functional. Furthermore, leveraging RL, AdvTG automatically selects traffic fields that exhibit more robust adversarial properties. Experimental results show that AdvTG achieves over 40\% attack success rate (ASR) across six detection models on four base datasets and two extended datasets, significantly outperforming other adversarial attack methods.

Data summarization tasks are often modeled as $k$-clustering problems, where the goal is to choose $k$ data points, called cluster centers, that best represent the dataset by minimizing a clustering objective. A popular objective is to minimize the maximum distance between any data point and its nearest center, which is formalized as the $k$-center problem. While in some applications all data points can be chosen as centers, in the general setting, centers must be chosen from a predefined subset of points, referred as facilities or suppliers; this is known as the $k$-supplier problem. In this work, we focus on fair data summarization modeled as the fair $k$-supplier problem, where data consists of several groups, and a minimum number of centers must be selected from each group while minimizing the $k$-supplier objective. The groups can be disjoint or overlapping, leading to two distinct problem variants each with different computational complexity. We present $3$-approximation algorithms for both variants, improving the previously known factor of $5$. For disjoint groups, our algorithm runs in polynomial time, while for overlapping groups, we present a fixed-parameter tractable algorithm, where the exponential runtime depends only on the number of groups and centers. We show that these approximation factors match the theoretical lower bounds, assuming standard complexity theory conjectures. Finally, using an (anonymous) open-source implementation, we demonstrate the scalability of our algorithms on large synthetic datasets and assess the price of fairness on real-world data, comparing solution quality with and without fairness constraints.

Decentralized learning (DL) is an emerging technique that allows nodes on the web to collaboratively train machine learning models without sharing raw data. Dealing with stragglers, i.e., nodes with slower compute or communication than others, is a key challenge in DL. We present DivShare, a novel asynchronous DL algorithm that achieves fast model convergence in the presence of communication stragglers. DivShare achieves this by having nodes fragment their models into parameter subsets and send, in parallel to computation, each subset to a random sample of other nodes instead of sequentially exchanging full models. The transfer of smaller fragments allows more efficient usage of the collective bandwidth and enables nodes with slow network links to contribute with at least some of their model parameters quickly. By theoretically proving the convergence of DivShare, we provide, to the best of our knowledge, the first formal proof of convergence for a DL algorithm that accounts for the effects of asynchronous communication with delays. We experimentally evaluate DivShare against two state-of-the-art DL baselines, AD-PSGD and Swift, and with two standard datasets, CIFAR-10 and Movielens. We find that DivShare with communication stragglers lowers time-to-accuracy by up to 3.9x compared to AD-PSGD on the CIFAR-10 dataset. Compared to baselines, DivShare also achieves up to 19.4% better accuracy and 9.5% lower test loss on the CIFAR-10 and Movielens datasets, respectively.

With the adoption of deep learning models to low-power, small-memory edge devices, energy consumption and storage usage of such models has become a key concern. The problem acerbates even further with ever-growing data and equally-matched bulkier models. This concern is particularly pronounced for graph data due to its quadratic storage, irregular (non-grid) geometry, and very large size. Typical graph data, such as road networks, infrastructure networks, social networks easily exceeds millions of nodes, and several gigabytes of storage is needed just to store the node embedding vectors, let alone the model parameters. In recent years, the memory issue has been addressed by moving away from memory-intensive double precision floating-point arithmetic towards single-precision or even half-precision, often by trading-off marginally small performance. Along this effort, we propose Node2binary, which embeds graph nodes in as low as 128 binary bits, which drastically reduces the memory footprint of vertex embedding vectors by several order of magnitude. Node2binary leverages a fast community detection algorithm to covert the given graph into a hierarchical partition tree and then find embedding of graph vertices in binary space by solving a combinatorial optimization (CO) task over the tree edges. CO is NP-hard, but Node2binary uses an innovative combination of discrete gradient descent and randomization to solve this effectively and efficiently. Our extensive experiments over four real-world graphs show that Node2binary achieves competitive performances compared to the state-of-the art graph embedding methods in both node classification and link prediction tasks.

Large language models (LLMs) are increasingly leveraged as foundational backbones in the development of advanced recommender systems, offering enhanced capabilities through their extensive knowledge and reasoning. Existing LLM-based recommender systems (RSs) often face challenges due to the significant differences between the linguistic semantics of pre-trained LLMs and the collaborative semantics essential for RSs. Typically, these systems apply pre-trained linguistic semantics while learning collaborative semantics from scratch using the LLM-Backbone. However, as LLM architectures are not inherently tailored for recommendation tasks, this approach results in inefficient learning of collaborative information, poor understanding of result correlations, and a failure to leverage traditional RSs features effectively. To address these challenges, we propose LLM-BS, a decoder-only LLM-based generative recommendation framework that integrates endogenous and exogenous Behavioral and Semantic information in a non-intrusive manner. Specifically, we propose 1) a dual-source, knowledge-rich item indexing scheme that integrates indexing sequences for exogenous signals, enabling efficient link-wide processing; 2) a multi-scale reconfiguration alignment that non-intrusively guides the model toward a deeper understanding of both collaborative and semantic signals; 3) an Annealing Adapter designed to finely balance the model’s recommendation performance with its comprehension capabilities. We demonstrate LLM-BS’s effectiveness through rigorous testing on three public benchmarks.

Web applications often include third-party content and scripts to personalize a user's online experience. These scripts have unrestricted access to a user's private data stored in the browser's persistent storage like cookies, localstorage and IndexedDB, associated with the host page. Various mechanisms have been implemented to restrict access to these storage objects, e.g., content security policy, the HttpOnly attribute with cookies, etc. However, the existing mechanisms provide an all-or-none access and do not work in scenarios where web applications need to allow controlled access to cookies and localstorage objects by third-party scripts. If some of these scripts behave maliciously, they can easily access and modify private user information that are stored in the browser objects. The goal of our work is to design a mechanism to enforce fine-grained control of persistent storage objects. We perform an empirical study of persistent storage access by third-party scripts on Tranco's top 10,000 websites and find that 89.84% of all cookie accesses, 90.98% of all localstorage accesses and 72.49% of IndexedDB accesses are done by third-party scripts. Our approach enforces least privilege access for third-party scripts on these objects to ensure their security by attaching labels to the storage objects that specify which domains are allowed to read from and write to these objects. We implement our approach on the Firefox browser and show that it effectively blocks scripts from other domains, which are not allowed access, based on these labels, from accessing the storage objects. We show that our enforcement results in some functionality breakage in websites with the default settings, which can be fixed by correctly labeling the storage objects used by the third-party scripts.

Recommender Systems (RS) aim to generate personalized ranked lists for each user and are also evaluated using ranking metrics. Although personalized ranking is a fundamental aspect of RS, this critical property is often overlooked in the design of model architectures. To address this issue, we propose Rankformer, a ranking-inspired recommendation model. The architecture of Rankformer is inspired by the gradient of the ranking objective, embodying a unique (graph) transformer architecture --- it leverages global information from all users and items to produce more informative representations, and employs specific attention weights to guide the evolution of embeddings towards improved ranking performance. We further develop an acceleration algorithm for Rankformer, reducing its complexity to a linear level with respect to the number of positive instances. Extensive experimental results demonstrate that Rankformer outperforms state-of-the-art methods.

We introduce ColaCare, a framework that enhances Electronic Health Record (EHR) modeling through multi-agent collaboration driven by Large Language Models (LLMs). Our approach seamlessly integrates domain-specific expert models with LLMs to bridge the gap between structured EHR data and text-based reasoning. Inspired by the Multidisciplinary Team (MDT) approach used in clinical settings, ColaCare employs two types of agents: DoctorAgents and a MetaAgent, which collaboratively analyze patient data. Expert models process and generate predictions from numerical EHR data, while LLM agents produce reasoning references and decision-making reports within the MDT-driven collaborative consultation framework. The MetaAgent orchestrates the discussion, facilitating consultations and evidence-based debates among DoctorAgents, simulating diverse expertise in clinical decision-making. We additionally incorporate the Merck Manual of Diagnosis and Therapy (MSD) medical guideline within a retrieval-augmented generation (RAG) module for medical evidence support, addressing the challenge of knowledge currency. Extensive experiments conducted on three EHR datasets demonstrate ColaCare's superior performance in clinical mortality outcome and readmission prediction tasks, underscoring its potential to revolutionize clinical decision support systems and advance personalized precision medicine. The code, complete prompt templates, case studies are publicly available at the anonymous link: https://colacare.netlify.app.

Approximate nearest neighbor (ANN) search is fundamental in various applications such as information retrieval. To enhance efficiency, partition-based methods are proposed to narrow the search space by probing partial partitions, yet they face two common issues. First, in the query phase, a widely adopted strategy in existing studies such as IVF is to probe partitions based on the distance ranks of a query to partition centroids. This inevitably leads to irrelevant partition probing, since data distribution is not considered. Second, in the partition construction phase, all the partition-based methods have the boundary problem that separates a query's $k$NN to multiple partitions and produces a long-tailed $k$NN distribution, degrading the optimal $nprobe$ (i.e., the number of probing partitions) and the search efficiency. To address these problems, we propose LIRA, a LearnIng-based queRy-aware pArtition framework. Specifically, we propose a probing model to learn and directly probe the partitions containing the $k$NN of a query. Probing partitions with the model can reduce probing waste and allow for query-aware probing with query-specific $nprobe$. Moreover, we incorporate the probing model into a learning-based redundancy strategy to mitigate the adverse impact of the long-tailed $k$NN distribution on partition probing. Extensive experiments on real-world vector datasets demonstrate the superiority of LIRA in the trade-off among accuracy, latency, and query fan-out. The results show that LIRA consistently reduces the latency and the query fan-out up to 30\%.

The core of the modern recommender systems lies in learning high-quality embedding representations of users and items to investigate their positional relations in the feature space. Unfortunately, data sparsity caused by difficult-to-access interaction data severely limits the effectiveness of recommender systems. Faced with such a dilemma, various types of self-supervised learning methods have been introduced into recommender systems in an attempt to alleviate the data sparsity through distribution modeling or data augmentation. However, most data augmentation relies on elaborate manual design, which is not only not universal, but the bloated and redundant augmentation process may significantly slow down model training progress. To tackle these limitations, we propose a novel Dual Mixing-based Recommendation Framework (MixRec) to empower data augmentation as we wish. Specifically, we propose individual mixing and collective mixing, respectively. The former aims to provide a new positive sample that is unique to the target (user or item) and to make the pair-wise recommendation loss benefit from it, while the latter aims to portray a new sample that contains group properties in a batch. The two mentioned mixing mechanisms allow for data augmentation with only one parameter that does not need to be set multiple times and can be done in linear time complexity. Besides, we propose the dual-mixing contrastive learning to maximize the utilization of these new-constructed samples to enhance the consistency between pairs of positive samples. Experimental results on four real-world datasets demonstrate the effectiveness of MixRec in terms of recommendation performance, training efficiency, sparsity resistance, and usability.

Information disclosure can compromise privacy when revealed information is correlated with private information. We consider the notion of inferential privacy, which measures privacy leakage by bounding the inferential power a Bayesian adversary can gain by observing a released signal. Our goal is to devise an inferentially-private private information structure that maximizes the informativeness of the released signal, following the Blackwell ordering principle, while adhering to inferential privacy constraints. To achieve this, we devise an efficient release mechanism that achieves the inferentially-private Blackwell optimal private information structure for the setting where the private information is binary. Additionally, we propose a programming approach to compute the optimal structure for general cases given the utility function. The design of our mechanisms builds on our geometric characterization of the Blackwell-optimal disclosure mechanisms under privacy constraints, which may be of independent interest.

The rapid proliferation of fake news on social media threatens social stability, creating an urgent demand for more effective detection methods. While many promising approaches have emerged, most rely on content analysis with limited semantic depth, leading to suboptimal comprehension of news content. To address this limitation, capturing broader-range semantics is essential yet challenging, as it introduces two primary types of noise: fully connecting sentences in news graphs often adds unnecessary structural noise, while highly similar but authenticity-irrelevant sentences introduce feature noise, complicating the detection process. To tackle these issues, we propose BREAK, a broad-range semantics model for fake news detection that leverages a fully connected graph to capture comprehensive semantics while employing dual denoising modules to minimize both structural and feature noise. The semantic structure denoising module balances the graph’s connectivity by iteratively refining it between two bounds: a sequence-based structure as a lower bound and a fully connected graph as the upper bound. This refinement uncovers label-relevant semantic interrelations structures. Meanwhile, the semantic feature denoising module reduces noise from similar semantics by diversifying representations, aligning distinct outputs from the denoised graph and sequence encoders using KL-divergence to achieve feature diversification in high-dimensional space. The two modules are jointly optimized in a bi-level framework, enhancing the integration of denoised semantics into a comprehensive representation for detection. Extensive experiments across four datasets demonstrate that BREAK significantly outperforms existing methods in identifying fake news. Code is available at https://anonymous.4open.science/r/BREAK.

Search result diversification (SRD), aimed at ensuring that selected documents in a ranking list cover a wide range of subtopics, is a significant and extensively studied problem in Web search and Information Retrieval. Existing methods primarily utilize a paradigm of "greedy selection", i.e., selecting one document with the highest diversity score at a time. These approaches tend to be inefficient and are easily trapped in a suboptimal state. In addition, some other methods optimize an approximation of the objective function, but the results still remain suboptimal. To address these challenges, we introduce \textbf{M}ulti-\textbf{A}gent reinforcement learning (MARL) for search result \textbf{DIV}ersity, which called \textbf{MA4DIV}. In this approach, each document is an agent and the search result diversification is modeled as a cooperative task among multiple agents. By modeling the SRD ranking problem as a cooperative MARL problem, this approach allows for directly optimizing the diversity metrics, such as $\alpha$-NDCG, while achieving high training efficiency. We conducted experiments on public TREC datasets and a large-scale dataset in the industrial setting. The results show that MA4DIV achieves substantial improvements in both effectiveness and efficiency than existing baselines, especially on the industrial scale dataset.

Advertisers are increasingly using automated bidding to optimize their ad campaigns on online advertising platforms. Autobidding allows an advertiser to optimize her objective subject to various constraints. In this paper, we design online autobidding algorithms to optimize value subject to ROI and budget constraints. We consider an item is being auctioned in each of $T$ rounds. We focus on one buyer with budget and ROI constraints in the stochastic setting: her value and highest competing bid faced are drawn i.i.d. from some unknown (joint) distribution in each round. We design low-regret bidding algorithms that bid on behalf of this buyer. Our main result is an algorithm with full information feedback (i.e., the highest competing bid is revealed after each round) that guarantees a near-optimal $\tilde O(\sqrt T)$ regret with respect to the best Lipschitz function that maps values to bids. The class of Lipschitz bidding functions is rich enough to best respond to many correlation structures between value and highest competing bid, e.g., positive or negative correlation. Our result applies to a wide range of auctions, most notably any mixture of first- and second-price auctions. In addition, our result holds for both value-maximizing buyers and quasi-linear utility-maximizing buyers. We also study the bandit setting, where the algorithm only observes whether the bidder wins the auction or not. In this setting, we show an $\Omega(T^{2/3})$ regret lower bound for first-price auctions, showing a significant disparity between the full information and bandit settings. We also design an algorithm with a regret bound of $\tilde O(T^{3/4})$ when the value distribution is known and is independent of the highest competing bid.

Trajectory Similarity Join (TS-Join), as a fundamental operation in trajectory data analytics, has been extensively investigated by existing studies in data science community. However, existing solutions are almost designed for offline static trajectories, which cannot guarantee real-time feedback. In addition, the join results retrieved from existing solutions generally contains a large proportion of out-of-date similar pairs, making them inapplicable to evolving trajectories. In this light, we study a novel problem of online time-aware trajectory similarity join: Given a stream of evolving trajectories, we aim to dynamically discover trajectory pairs whose spatio-temporal similarity is no less than a specified threshold in a real-time manner. We innovatively introduce a time-aware exponential-decaying similarity function to eliminate out-of-date results. To support real-time querying over large populations of trajectories, we develop a Parallel Online Trajectory Similarity Join (POTSJ) framework incorporating with well-designed workload balancing techniques. We further enhance join efficiency through effective pruning strategies and tailored approximation techniques. The POTSJ framework we propose, which incorporates these elements, is capable of processing online TS-Join while simultaneously satisfying three key objectives: real-time result updates, comprehensive trajectory evaluation, and scalability. Extensive experiments on real-world datasets validate the efficiency and scalability superiority of our POTSJ framework in processing online TS-Join.