WWW 2025 Papers

Multimodal Knowledge Graphs (MMKG) models integrate multimodal contexts to improve link prediction performance. All existing MMKG models follow the transductive setting with a fixed predefined set, meaning that all the entities, relations, and multimodal information in the test graph are observed during training. This hinders their generalization to real-world MMKG with unseen entities and relations. Intuitively, a MMKG model trained on DBpedia cannot infer on Freebase. To address above limitations, we make the first attempt towards inductive learning for MMKG and propose a multimodal \underline{\textbf{Ind}}uctive \underline{\textbf{MMKG}} model (\textbf{IndMKG}) that is \textit{\textbf{universal}} and \textit{\textbf{transferable}} to any MMKG. Distinct from existing transductive methods, our model does not rely on specific trained embeddings; instead, IndMKG generates adaptive embeddings conditioned on any new MMKG via multimodal prototypes. Specifically, we construct class-adaptive prototypes to appropriately characterize the multimodal feature distribution of the given graph and equip IndMKG with robust adaptability to multimodal information across MMKGs. In addition, IndMKG learns non-specific structural embeddings based on meta relations. Such strategies tackle the challenge of notable multimodal feature discrepancies in cross-graph induction and allow the pre-trained IndMKG model to effectively zero-shot generalize to any MMKG. The strong performance in both inductive and transductive settings, across more than 20+ different scenarios, confirms the effectiveness and robustness of IndMKG. Our code is released at https://anonymous.4open.science/r/IndMKG.

Entity Matching (EM) automates the discovery of identity links between entities within different Knowledge Graphs (KGs). Link keys are crucial for EM, serving as rules allowing to identify identity links across different KGs, possibly described using different ontologies. However, the approach for extracting link keys struggles to scale on large KGs. While embedding-based EM methods efficiently handle large KGs they lack explainability. This paper proposes a novel hybrid EM approach to guarantee the scalability link key extraction approach and improve the explainability of embedding-based EM methods. First, embedding-based EM approaches are used to sample the KGs based on the identity links they generate, thereby reducing the search space to relevant sub-graphs for link key extraction. Second, rules (in the form of link keys) are extracted to explain the generation of identity links by the embedding-based methods. Experimental results demonstrate that the proposed approach allows link key extraction to scale on large KGs, preserving the quality of the extracted link keys. Additionally, it shows that link keys can improve the explainability of the identity links generated by embedding-methods, allowing for the regeneration of 77% of the identity links produced for a specific EM task, thereby providing an approximation of the reasons behind their generation.

Machine learning-driven rankings, where individuals (or items) are ranked in response to a query, mediate search exposure or attention in a variety of safety-critical settings. Thus, it is important to ensure that such rankings are fair. Under the goal of equal opportunity, attention allocated to an individual on a ranking interface should be proportional to their relevance across search queries. In this work, we examine amortized fair ranking -- where relevance and attention are cumulated over a sequence of user queries to make fair ranking more feasible. Unlike prior methods that operate on expected amortized attention for each individual, we define new divergence-based measures for attention distribution-aware fairness in ranking (DistFaiR), characterizing unfairness as the divergence between the distribution of attention and relevance corresponding to an individual over time. This allows us to propose new definitions of unfairness, which are more reliable at test time and outperform prior fair ranking baselines. Second, we prove that group fairness is upper-bounded by individual fairness under this definition for a useful sub-class of divergence measures, and experimentally show that maximizing individual fairness through an integer linear programming-based optimization is often beneficial to group fairness. Lastly, we find that prior research in amortized fair ranking ignores critical information about queries, potentially leading to a fairwashing risk in practice by making rankings appear more fair than they actually are.

In an edge-assisted federated learning (FL) system, edge servers aggregate the local models from the clients within their coverage areas to produce intermediate models for the production of the global model. This significantly reduces the communication overhead incurred during the FL process. To accelerate model convergence, FedEdge, the state-of-the-art edge-assisted FL system, trains clients' models in local federations when they wait for the global model in each training round. However, our investigation reveals that it drives the global model towards clients with excessive local training, causing model drifts that undermine model performance for other clients. To tackle this problem, this paper presents Maverick, a new edge-assisted FL system that mitigates model drifts by training personalized local models for clients through contrastive local training. It introduces a model-contrastive loss to facilitate personalized local federated training by driving clients' local models away from the global model and close to their corresponding intermediate models. In addition, Maverick includes anomalous models in contrastive local training as negative samples to accelerate the convergence of clients' local models. Extensive experiments are conducted on three widely-used public datasets to comprehensively evaluate the performance of Maverick. Compared to state-of-the-art edge-assisted FL systems, Maverick accelerates model convergence by up to 16.2x and improves model accuracy by up to 12.7%.

The InterPlanetary File System (IPFS) is a pioneering effort for Web 3.0, well-known for its decentralized infrastructure. However, some recent studies have shown that IPFS exhibits a high degree of centralization and has integrated centralized components for better performance. While this change contradicts the core decentralized ethos of IPFS and introduces risks of hurting the data replication level and thus availability, it also opens some opportunities for better data management and cost savings through deduplication. To explore these challenges and opportunities, we start by collecting an extensive dataset of IPFS internal traffic spanning the last three years with 20+ billion messages. By analyzing this long-term trace, we obtain a more complete and accurate view of how the status of centralization evolves over an extended period. In particular, (1) IPFS shows a low replication level in general, with only about 2.71% of data files replicated more than 5 times. While increasing replication enhances lookup performance and data availability, it adversely affects downloading throughput due to the over- head involved in managing peer connections, (2) there is a clear growing trend in centralization within IPFS in the last 3 years, with just 5% of peers now hosting over 80% of the content, significantly decreasing from 21.38% 3 years ago, which is largely driven by the increase of cloud nodes, (3) the IPFS default deduplication strategy using Fixed-Size Chunking (FSC) is largely inefficient, especially with the current 256KB chunk size, achieving nearly zero efficiency. Although Content-Defined Chunking (CDC) with smaller chunks could save significant storage (about 1.8 PB) and cost, it could impact user performance negatively. We thus design and evaluate a new metadata format that optimizes deduplication without compromising performance.

Reranking is significant for recommender systems due to its pivotal role in refining recommendation results. To meet diverse reranking requirements in practical applications, numerous reranking models have emerged, which not only prioritize accuracy but also consider additional aspects such as diversity and fairness, etc. However, most of the existing models struggle to strike a harmonious balance between these diverse aspects at the model level. Additionally, the scalability and personalization of these models are often limited by their complexity and a lack of attention to the varying importance of different aspects in diverse reranking scenarios. To address these issues, we propose LLM4Rerank, a comprehensive LLM-based reranking framework designed to bridge the gap between various reranking aspects while ensuring scalability and personalized performance. Specifically, we abstract different aspects into distinct nodes and construct a fully connected graph for LLM to automatically consider aspects like accuracy, diversity, fairness, and more, all in a coherent Chain-of-Thought (CoT) process. To further enhance personalization during reranking, we facilitate a customizable input mechanism that allows fine-tuning of LLM's focus on different aspects according to specific reranking needs. Experimental results on three widely used public datasets demonstrate that LLM4Rerank outperforms existing state-of-the-art reranking models across multiple aspects. The implementation code is available for reproducibility.

Conversational Recommender System (CRS) leverages real-time feedback from users to dynamically model their preferences, thereby enhancing the system's ability to provide personalized recommendations and improving the overall user experience. CRS has demonstrated significant promise, prompting researchers to concentrate their efforts on developing user simulators that are both more realistic and trustworthy. The emergence of Large Language Models (LLMs) has marked the onset of a new epoch in computational capabilities, exhibiting human-level intelligence in various tasks. Research efforts have been made to utilize LLMs for building user simulators to evaluate the performance of CRS. Although these efforts showcase innovation, they are accompanied by certain limitations. In this work, we introduce a Controllable, Scalable, and Human-Involved (CSHI) simulator framework that manages the behavior of user simulators across various stages via a plugin manager. CSHI customizes the simulation of user behavior and interactions to provide a more lifelike and convincing user interaction experience. Through experiments and case studies in two conversational recommendation scenarios, we show that our framework can adapt to a variety of conversational recommendation settings and effectively simulate users' personalized preferences. Consequently, our simulator is able to generate feedback that closely mirrors that of real users. This facilitates a reliable assessment of existing CRS studies and promotes the creation of high-quality conversational recommendation datasets.

Online hatred has become an increasingly pervasive issue, affecting individuals and communities across various digital platforms. To combat hate speech in such platforms, counter narratives (CNs) are regarded as an effective method. In recent years, there has been growing interest in using generative AI tools to construct CNs. However, most of the generative models produce generic responses to hate speech and can hallucinate, reducing their effectiveness. To address the above limitations, we propose a counter narrative generation method that enhances CNs by providing non-aggressive, fact-based narratives with relevant background knowledge from two distinct sources, including a web search module. Furthermore we conduct a comprehensive evaluation using multiple metrics, including LLM-based measures for persuasion, factuality, and informativeness, along with human and traditional NLP evaluations. Our method significantly outperforms baselines, achieving an average factuality score of 0.915, compared to 0.741 and 0.701 for competitive baselines, and performs well in human evaluations.

Short Video Hate Detection (SVHD) is increasingly vital as hateful content — such as racial and gender-based discrimination — spreads rapidly across platforms like TikTok, YouTube Shorts, and Instagram Reels. Existing approaches face significant challenges: hate expressions continuously evolve, hateful signals are dispersed across multiple modalities (audio, text, and vision), and the contribution of each modality varies across different hate content. To address these issues, we introduce MoRE (Mixture of Retrieval-augmented multimodal Experts), a novel framework designed to enhance SVHD. MoRE employs specialized multimodal experts for each modality, leveraging their unique strengths to identify hateful content effectively. To ensure model's adaptability to rapidly evolving hate content, MoRE leverages contextual knowledge extracted from relevant instances retrieved by a powerful joint multimodal video retriever for each target short video. Moreover, a dynamic sample-sensitive integration network adaptively adjusts the importance of each modality on a per-sample basis, optimizing the detection process by prioritizing the most informative modalities for each instance. Our MoRE adopts an end-to-end training strategy that jointly optimizes both expert networks and the overall framework, resulting in nearly a twofold improvement in training efficiency, which in turn enhances its applicability to real-world scenarios. Extensive experiments on three benchmarks demonstrate that MoRE surpasses state-of-the-art baselines, achieving an average improvement of 6.91% in macro-F1 score across all datasets.

The $q$-parameterized magnetic Laplacian serves as the foundation of directed graph (digraph) convolution from a spectral perspective, enabling this kind of digraph neural network (MagDG) to encode node features and structural insights by complex-domain message passing. As a generalization of undirected methods, MagDG shows superior capability in modeling intricate web-scale topology and offers greater application potential. Despite the great success achieved by existing MagDGs, limitations still exist: (1) {Hand-crafted $q$}: The performance of MagDGs depends on selecting an appropriate $q$-parameter to construct suitable graph propagation equations in the complex domain. This parameter tuning, driven by downstream tasks, limits model flexibility and significantly increases manual effort. (2) {Coarse Message Passing}: Most approaches treat all nodes with the same complex-domain propagation and aggregation rules, neglecting their unique digraph contexts. This oversight results in sub-optimal performance. To address the above issues, we propose two key techniques: (1) MAP is crafted to be a plug-and-play complex-domain propagation optimization strategy in the context of digraph learning, enabling seamless integration into any MagDG to improve predictions while enjoying high running efficiency. (2) MAP++ is a new digraph learning framework, further incorporating a learnable mechanism to achieve adaptively edge-wise propagation and node-wise aggregation in the complex domain for better performance. Extensive experiments on 12 datasets demonstrate that MAP enjoys flexibility for it can be incorporated with any MagDG, and scalability as it can deal with web-scale digraphs. MAP++ achieves SOTA predictive performance on 4 different downstream tasks.

Centrality measures are essential for identifying important nodes and edges within a network. In this paper, we focus on two forest-based centrality measures on undirected graphs: forest node centrality (FNC) and forest edge centrality (FEC), which capture the influence of nodes and edges through their participation in spanning forests. Both centrality measures can be represented using entries of the forest matrix. To address the challenge of computing the two measures on large networks, we propose two scalable algorithms from different perspectives. The first algorithm $\textbf{IFGN}$ combines two variance reduction techniques to approximate the entries of the forest matrix, which is applicable to both FNC and FEC. The second algorithm $\textbf{FECE}$ incorporates a new physical interpretation of FEC, allowing for a better overall estimation. We provide error guarantees for both algorithms and demonstrate their efficiency and effectiveness through extensive experiments on various real-world networks.

Multivariate time series anomaly detection is essential for failure management in web application operations, as it directly influences the effectiveness and timeliness of implementing remedial or preventive measures. This task is often framed as a semi-supervised learning problem, where only normal data are available for model training, primarily due to the labor-intensive nature of data labeling and the scarcity of anomalous data. Existing semi-supervised methods often detect anomalies by capturing intra-variate temporal dependencies and/or inter-variate relationships to learn normal patterns, flagging timestamps that deviate from these patterns as anomalies. However, these approaches often fail to capture salient intra-variate temporal and inter-variate dependencies in time series due to their focus on excessively fine granularity, leading to suboptimal performance. In this study, we introduce MtsCID, a novel semi-supervised multivariate time series anomaly detection method. MtsCID employs a dual network architecture: one network operates on the attention maps of multi-scale intra-variate patches for coarse-grained temporal dependency learning, while the other works on variates to capture coarse-grained inter-variate relationships through convolution and interaction with sinusoidal prototypes. This design enhances the ability to capture the patterns from both intra-variate temporal dependencies and inter-variate relationships, resulting in improved performance. Extensive experiments across seven widely used datasets demonstrate that MtsCID achieves performance comparable or superior to state-of-the-art benchmark methods.

In this study, we reveal, for the first time, popular online social networks (especially Twitter) are being extensively abused by miscreants to promote illicit goods and services of diverse categories. This study is made possible by multiple machine learning tools that are designed to detect and analyze Posts of Illicit Promotion (PIPs) as well as revealing their underlying promotion campaigns. Particularly, we observe that PIPs are prevalent on Twitter, along with extensive visibility on other three popular OSNs including YouTube, Facebook, and TikTok. For instance, applying our PIP hunter to the Twitter platform for 6 months has led to the discovery of 12 million distinct PIPs which are widely distributed in 5 major natural languages and 10 illicit categories, e.g., drugs, data leakage, gambling, and weapon sales. Along the discovery of PIPs are 580K Twitter accounts publishing PIPs as well as 37K distinct instant messaging accounts that are embedded in PIPs and serve as next hops of communication with prospective customers. Also, an arms race between Twitter and illicit promotion operators is also observed. Especially, 90% PIPs can survice the first two months since getting published on Twitter, which is likely due to the diverse evasion tactics adopted by miscreants to masquerade PIPs.

Browser fingerprinting is a tracking technique that collects attributes and calls functions from the browser’s APIs. Unlike cookies, browser fingerprints are difficult to evade or delete, raising significant privacy concerns for users as they can be used to re-identify individuals over browsing sessions without their consent. Yet, there has been limited research on the impact of browser configuration settings on these fingerprints. This paper introduces FP-Rainbow, a novel approach to systematically explore and map the configuration space of Chromium-based web browsers aiming to identify the impact of configuration parameters on browser fingerprints and their changes over time. We explore 1,748 configuration parameters (switches) and identify their impact on the browser’s BOM (Browser Object Model). By collecting and analyzing over 61,000 fingerprints from 18 versions of Chromium, our study reveals that 32 to 56 of these configuration parameters (depending on versions), such as disable-3d-apis or disable-notifications, influence the fingerprint of a web browser. FP-Rainbow also proves efficient in identifying browser configuration parameters from unknown fingerprints, achieving an average successful identification rate of 84% when considering a single configuration parameter and 78% when multiple parameters are involved, across all evaluated browser versions. These findings emphasize the importance of measuring the impact of configuration parameters on browsers to develop safer and more ethical web browsers.

Owing to the unprecedented capability in semantic understanding and logical reasoning, the large language models (LLMs) have shown fantastic potential in developing the next-generation sequential recommender systems (RSs). However, on one hand, existing LLM-based sequential RSs mostly separate the index generation from the sequential recommendation, leading to insufficient integration between the semantic information and the collaborative information. On the other hand, the neglect of the user-related information hinders the LLM-based sequential RSs from exploiting the high-order user-item interaction patterns implicating in user behavior. In this paper, we propose the End-to-End Dual Dynamic (ED$^2$) recommender, the first LLM-based sequential recommender system which adopts the dual dynamic index mechanism, targeting at resolving the above limitations simultaneously. The dual dynamic index mechanism can not only assembly the index generation and the sequential recommendation into an unified LLM-backbone pipeline, but also make it practical for the LLM-based sequential recommender to take advantage of the user-related information. Specifically, to facilitate the LLMs comprehension ability to the dual dynamic index, we propose a multi-grained token regulator which constructs alignment supervision based on the LLMs semantic knowledge across multiple representation granularities. Moreover, the associated user collection data and a series of novel instruction tuning tasks are specially customized to exploit the user historical behavior in depth and capture the high-order user-item interaction patterns. Extensive experiments on three public datasets demonstrate the superiority of ED$^2$, achieving an average improvement of 19.41\% in Hit-Rate and 20.84\% in NDCG metric.

The 21st century has already witnessed so many outbreaks with pandemic potential, including SARS (2002), H1N1 (2009), MERS (2012), Ebola (2014), Zika virus (2015), and the COVID-19 pandemic (2019). Using 60 million geotagged Sina Weibo tweets covering over 20 million active accounts, we investigate the collective emotional dynamics on social media in the most recent global pandemic, i.e., COVID-19. This research features two highlights: (1) It focuses on the Chinese population located in the initial epicenter of the pandemic. (2) It examines the initial year after the pandemic outbreak, a critical period where emotions were most intense due to the uncertainty and rapid developments related to the crisis. Using cross-disciplinary methods, we reveal a positive connection between online emotional resonance and geographic proximity, demonstrating a direct mapping between virtual network distances and physical spatial embedding. We propose a percolation-based index to measure the nationwide emotional resonance level with which we illustrate the significant economic impact of the global health issue. Finally, we identify a leader-follower pattern in emotional resonance fluctuations based on time-lag emotion correlations, revealing that less active regions play a crucial role in leading and responding to emotional changes. In the face of long COVID and emerging global health crises, our analysis elucidates how collective emotional resonance evolves, providing potential directions for online opinion interventions during global shocks.

Recent advances in Artificial Intelligence (AI) have introduced a new paradigm in Machine Learning (ML) model development: pre-training of foundation model and domain adaptation. Two groups lead in developing foundation model: closed-source developers and open-source community. As open-source community becomes increasingly engaged, the performance open-source models are catching up with closed-source models. However, this leaves domain deployers into a dilemma: use closed-source models via API access or host open-source models on proprietary hardware. Using closed-source models incurs recurring costs, while hosting open-source models incurs substantial hardware investments and potentially lagging advancements. This paper presents a game-theoretical model to examine the economic incentives behind the deployment choice and the impact of open-source engagement strategy on technology innovation. We find that the deployer consistently opts for closed-source APIs when the open-source community engages in the market reactively by maintaining a fixed performance ratio relative to closed-source advancements. However, open-source models can be favored when a proactive open-source community produces high-performance models independently. Also, we identify conditions under which engagement and competitiveness of the open-source community can foster or inhibit technological progress. These insights offer valuable implications for market regulation and the future of AI model innovation.

Snapshot technology is crucial for data protection and system recovery in virtualized environments, particularly with the growing need for continuous snapshots to maintain the integrity of long-running web-based and distributed applications. However, traditional snapshot methods often suffer from performance bottlenecks, and inefficient storage usage. These challenges are closely tied to the way memory pages are accessed during VM execution, where memory access patterns show significant disparities between frequently accessed "hot" pages and less-used "cold" pages.In this paper, we introduce HeatSnap, a continuous snapshot system designed to address these issues by leveraging the uneven access frequencies of memory pages. HeatSnap distinguishes between intensive hot pages and dirty pages, applying specialized snapshotting and storage strategies to optimize the handling of both hot and cold memory regions. This approach aims to optimize snapshot efficiency, minimize performance impact on the VM, and decrease storage costs.Our implementation of HeatSnap on QEMU/KVM demonstrates significant improvements in VM performance loss, snapshot duration, and storage efficiency compared to existing methods, as evidenced by evaluations on common web and cloud-based workloads.

Browser fingerprinting is a pervasive online tracking technique increasingly used for profiling and targeted advertising. Existing research on fingerprinting prevalence relies heavily on automated web crawls, which inherently struggle to replicate the nuances of human-computer interaction. This raises concerns about the accuracy of current understandings of real-world fingerprinting deployments. To that end, this paper presents a user study involving 30 participants over a 10-week period, capturing telemetry data from real browsing sessions across 3,000 top-ranked websites. Our findings reveal that automated crawls miss nearly half (47.8%) of the fingerprinting websites encountered by real users. This discrepancy mainly stems from crawlers' inability to access authentication-protected pages, circumvent bot detection mechanisms, and trigger fingerprinting scripts activated by specific user interactions. We also identify potential new fingerprinting vectors present in real user data but absent from automated crawls. Finally, we evaluate the effectiveness of federated learning for training browser fingerprinting detection models on real user data, demonstrating superior performance to models trained solely on automated crawl data.