Hypergraph-based distillation methods have been proposed to mitigate the high computational cost of Hypergraph Neural Networks (HGNNs) in modeling high-order relationships. However, most existing methods use static and uniform distillation strategies for all nodes and hyperedges, ignoring their individual characteristics. In addition, they neglect the student model's capability to independently extract useful internal features. As a result, they are not effective in transferring higher-order structural knowledge from the teacher. To overcome these limitations, we propose ARCHER, an Adaptive and Reinforcement-Guided Contrastive HypER graph Distillation framework that enables a lightweight MLP student model to outperform its HGNN teacher model. First, we design an adaptive strategy that leverages node- and hyperedge-level confidence to mediate error guidance from the teacher model. Second, we introduce a contrastive learning module that guides the student to learn from both the teacher's outputs and its own internal representations, producing more expressive embeddings. Finally, we propose a multi-armed bandit-based reinforcement learning module that dynamically balances multiple loss objectives during training. Experiments on six benchmark datasets demonstrate that our method outperforms existing hypergraph distillation methods.

Recently, hypergraph knowledge distillation has been proposed to alleviate the high computational cost of Hypergraph Neural Networks (HGNNs) when modeling high-order relationships in Web-related graph tasks. Its effectiveness primarily depends on the quality of knowledge transferred from the teacher and the representation capability of the student. However, existing methods remain limited on both sides. On the teacher side, most methods typically rely on a single HGNN teacher, which provides limited structural and semantic knowledge, thereby constraining the upper bound of the student's performance. The potential of exploiting multiple teachers in HGNNs remains largely underexplored. On the student side, existing methods ignore the student's capability to capture high-order semantic and structural information beyond simply imitating teacher outputs, leading to limited representation learning. To address these limitations, we propose MARCH, a framework for Multi-TeAcheR Contrastive Hypergraph Distillation, which advances semantic modeling and distillation for Web-scale structured data. Specifically, MARCH proposes a multi-teacher distillation strategy that adaptively transfers complementary knowledge from multiple teachers at both node and hyperedge levels, empowering the student model to learn richer and more discriminative representations and even outperform its teachers. Extensive experiments on six benchmark datasets demonstrate the superior performance of MARCH.

Social event detection involves identifying and categorizing important events from social media, which relies on labeled data, but annotation is costly and labor-intensive. To address this problem, we propose Augmentation framework for Social Event Detection (SED-Aug), a plug-and-play dual augmentation framework, which combines explicit text-based and implicit feature-space augmentation to enhance data diversity and model robustness. The explicit augmentation utilizes LLMs to enhance textual information through five diverse generation strategies. For implicit augmentation, we design five novel perturbation techniques that operate in the feature space on structural fused embeddings. These perturbations are crafted to keep the semantic and relational properties of the embeddings and make them more diverse. Specifically, SED-Aug outperforms the best baseline model by approximately 17.67% on the Twitter2012 dataset and by about 15.57% on the Twitter2018 dataset in terms of the average F1 score.

Social event detection (SED) is the task of identifying, categorizing, and tracking events from social data sources such as social media posts, news articles, and online discussions.Existing state-of-the-art (SOTA) SED models predominantly rely on graph neural networks (GNNs), which involve complex graph construction and time-consuming training processes, limiting their practicality in real-world scenarios.In this paper, we rethink the key challenge in SED: the informal expressions and abbreviations of short texts on social media platforms, which impact clustering accuracy.We propose a novel framework, LLM-enhanced Social Event Detection (LSED), which leverages the rich background knowledge of LLMs to address this challenge.Specifically, LSED utilizes LLMs to formalize and disambiguate short texts by completing abbreviations and summarizing informal expressions.Furthermore, we introduce hyperbolic space embeddings, which are more suitable for natural language sentence representations, to enhance clustering performance.Extensive experiments on two challenging realworld datasets demonstrate that LSED outperforms existing SOTA models, achieving improvements in effectiveness, efficiency, and stability.Our work highlights the potential of LLMs in SED and provides a practical solution for real-world applications.The code is available at GitHub 1 .

Nowadays social media is the primary platform for people to obtain news and share information. Combating online fake news has become an urgent task to reduce the damage it causes to society. Existing methods typically improve their fake news detection performances by utilizing textual auxiliary information (such as relevant retweets and comments) or simple structural information ( i.e. , graph construction). However, these methods face two challenges. First, an increasing number of users tend to directly forward the source news without adding comments, resulting in a lack of textual auxiliary information. Second, simple graphs are unable to extract complex relations beyond pairwise association in a social context. Given that real-world social networks are intricate and involve high-order relations, we argue that exploring beyond pairwise relations between news and users is crucial for fake news detection. Therefore, we propose constructing an attributed hypergraph to represent non-textual and high-order relations for user participation in news spreading. We also introduce a hypergraph neural network-based method called Hy-DeFake to tackle the challenges. Our proposed method captures semantic information from news content, credibility information from involved users, and high-order correlations between news and users to learn distinctive embeddings for fake news detection. The superiority of Hy-DeFake is demonstrated through experiments conducted on four widely-used datasets, and it is compared against nine baselines using four evaluation metrics. • We introduce an approach named Hy-DeFake by constructing an attributed hypergraph to represent the process of news spreading in online social networks. By abstracting fake news detection as hyperedge classification, we capture the intricate high-order relation between news and users in social contexts, enabling us to achieve accurate results. • The proposed Hy-DeFake utilizes hypergraph neural networks for fake news detection. It effectively captures the credibility information of users and the high-order correlation between news and users. Both of these aspects provide distinctive information that contributes to fake news detection. • Extensive experiments demonstrate that Hy-DeFake generally surpasses nine baseline methods on four real-world datasets from different domains. • We verify the positive correlation between news authenticity and user credibility. Users who spread fake news exhibit more intensive interaction compared to those who spread real news, resulting in the formation of a denser community.

Social events reflect the dynamics of society and, here, natural disasters and emergencies receive significant attention. The timely detection of these events can provide organisations and individuals with valuable information to reduce or avoid losses. However, due to the complex heterogeneities of the content and structure of social media, existing models can only learn limited information; large amounts of semantic and structural information are ignored. In addition, due to high labour costs, it is rare for social media datasets to include high-quality labels, which also makes it challenging for models to learn information from social media. In this study, we propose two hyperbolic graph representation-based methods for detecting social events from heterogeneous social media environments. For cases where a dataset has labels, we design aHyperbolicSocialEventDetection (HSED) model that converts complex social information into a unified social message graph. This model addresses the heterogeneity of social media, and, with this graph, the information in social media can be used to capture structural information based on the properties of hyperbolic space. For cases where the dataset is unlabelled, we design anUnsupervisedHyperbolicSocialEventDetection (UHSED). This model is based on the HSED model but includes graph contrastive learning to make it work in unlabelled scenarios. Extensive experiments demonstrate the superiority of the proposed approaches.

Since the inception of online fake news detection, the technique of natural language processing has predominantly been leading the field by utilizing text classification to discern veracity. From the network perspective, news traveling within a social network typically exhibits non-textual correlations aligned with the network of news propagation or news-user interaction. Therefore, with the advancement of graph learning, there have been emerging approaches incorporating graphs of social contexts as auxiliary information, of which the performance still relies on learning semantics from news text. As fake news becomes more adept at employing the writing pattern of real news and the assessment of certain news contents requires domain-specific knowledge, distinguishing real news from fake ones based on the text has become increasingly challenging. This raises a question: Can we debunk fake news without going through the text? Thus, this work aims to explore the feasibility of differentiating between real and fake news by capturing its relationships with other news and people in the network. We propose a method named ComE-DeFake which extracts intricate relations beyond pairwise of news and users in social contexts to detect fake news. Experimental results reveal that our method without using news text outperforms all baseline methods. This suggests that, if high-order complicated relations are fully captured, it is achievable to debunk fake news without analyzing its text.

Social events reflect changes in communities, such as natural disasters and emergencies. Detection of these situations can help residents and organizations in the community avoid danger and reduce losses. The complex nature of social messages makes social event detection on social media challenging. The challenges that have a greater impact on social media detection models are as follows: (1) the amount of social media data is huge but its availability is small; (2) social media data is a tree structure and traditional Euclidean space embedding will distort embedded features; and (3) the heterogeneity of social media networks makes existing models unable to capture rich information well. To solve the above challenges, we propose a Heterogeneous Information Graph representation via Hyperbolic space combined with an Automatic Meta-path selection (GraphHAM) model, an efficient framework that automatically selects the meta-path's weight and combines hyperbolic space to learn information on social media. In particular, we apply an efficient automatic meta-path selection technique and convert the selected meta-path into a vector, thereby reducing the requisite amount of labeled data for the model. We also design a novel Hyperbolic Multi-Layer Perceptron (HMLP) to further learn the semantic and structural information of social information. Extensive experiments show that GraphHAM can achieve outstanding performance on real-world data using only 20% of the whole dataset as the training set. Our code can be found on GitHub https://github.com/ZITAIQIU/GraphHAM.