ALAngsheng Li

Angsheng Li

*This is an algorithmically generated author record based on publicly available information.

Angsheng Li has a total of 45 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Structural Entropy Guided Meta-Learning for Few-Shot Node Classification

    by Xiang Chen, Kun Yue, Daliang Liu, Wenjie Liu, Liang Duan, Angsheng Li

    Few-shot node classification (FSNC) is a challenging task in graph analysis, where the goal is to classify unlabeled nodes in a graph using only a few labeled nodes as references. To tackle the label shortage problem, many meta-learning methods have been proposed to extract meta-knowledge from base classes with abundant labeled nodes and transfer the learned knowledge to classify nodes from novel classes. However, the theoretical foundation of meta-knowledge remains unexplored, and existing solutions often struggle when dealing with complex or noisy graphs. To address these issues, we propose a novel and effective meta-learning framework for FSNC based on structural information theory. First, we introduce the concept of minimal sufficient meta-knowledge, a theoretical principle inherited from information bottleneck, which optimally balances the expressiveness and robustness of the learned meta-knowledge. Guided by this principle, we develop a meta-learning model, named SE-FSNC, that extracts the minimal sufficient meta-knowledge using an encoding tree derived from the input graph with minimal structural entropy. We then propose an effective algorithm to train SE-FSNC by incorporating the encoding tree with graph contrastive learning. Extensive experiments on several datasets demonstrate the superiority of our model compared with other state-of-the-art methods.


  • Open Access

    Towards Compositional Generalization of LLMs via Skill Taxonomy Guided Data Synthesis

    by Yifan Wei, Li Du, Xiaoyan Yu, Yang Feng, Angsheng Li

    Large Language Models (LLMs) and agent-based systems often struggle with compositional generalization due to a data bottleneck in which complex skill combinations follow a long-tailed, power-law distribution, limiting both instruction-following performance and generalization in agent-centric tasks. To address this challenge, we propose STEPS, a Skill Taxonomy guided Entropy-based Post-training data Synthesis framework for generating compositionally challenging data. STEPS explicitly targets compositional generalization by uncovering latent relationships among skills and organizing them into an interpretable, hierarchical skill taxonomy using structural information theory. Building on this taxonomy, we formulate data synthesis as a constrained information maximization problem, selecting skill combinations that maximize marginal structural information within the hierarchy while preserving semantic coherence. Experiments on challenging instruction-following benchmarks show that STEPS outperforms existing data synthesis baselines, while also yielding improved compositional generalization in downstream agent-based evaluations.

  • Proactive Bot Detection Based on Structural Information Principles

    by Xianghua Zeng, Hao Peng, Angsheng Li

    Bot detection is crucial for combating misinformation and preserving the authenticity of online interactions on social media. However, the increasing sophistication of bots in mimicking genuine accounts and evading detection has created an ongoing arms race between detection systems and modeling techniques. In this paper, we propose a novel Structural Information principles-based Adversarial framework, namely SIAMD, designed to Model bot behaviors and achieve proactive Detection. This framework begins by organizing multi-relational interactions between user accounts and social messages into a unified heterogeneous structure, incorporating structural entropy to quantify the uncertainty inherent in historical activities. The high-dimensional entropy is then minimized to uncover a layered hierarchy within account communities, which facilitates activity determination and account selection in behavioral modeling for bot accounts. For each modeled bot and its selected account, SIAMD extracts historical messages and user descriptions to construct prompts and integrates large language models to generate the associated message content. By embedding synthetic message vertices and establishing multi-relational interactions within the original heterogeneous network, SIAMD achieves network evolution in both structure and content, thereby enhancing graph-based proactive detection in an adversarial manner. Extensive comparative experiments on well-established real-world datasets demonstrate that SIAMD significantly and consistently outperforms state-of-the-art detection baselines for social bots in terms of effectiveness, generalizability, robustness, and interpretability.


  • Open Access

    Hyperbolic Continuous Structural Entropy for Hierarchical Clustering

    by Guangjie Zeng, Hao Peng, Angsheng Li, Li Sun, Chunyang Liu, Shengze Li, Yicheng Pan, Philip S. Yu

    Hierarchical clustering is a fundamental machine-learning technique for grouping data points into dendrograms. However, existing hierarchical clustering methods encounter two primary challenges: 1) Most methods specify dendrograms without a global objective. 2) Graph-based methods often neglect the significance of graph structure, optimizing objectives on complete or static predefined graphs. In this work, we propose Hyperbolic Continuous Structural Entropy neural networks, namely HypCSE, for structure-enhanced continuous hierarchical clustering. Our key idea is to map data points in the hyperbolic space and minimize the relaxed continuous structural entropy (SE) on structure-enhanced graphs. Specifically, we encode graph vertices in hyperbolic space using hyperbolic graph neural networks and minimize approximate SE defined on graph embeddings. To make the SE objective differentiable for optimization, we reformulate it into a function using the lowest common ancestor (LCA) on trees and then relax it into continuous SE (CSE) by the analogy of hyperbolic graph embeddings and partitioning trees. To ensure a graph structure that effectively captures the hierarchy of data points for CSE calculation, we employ a graph structure learning (GSL) strategy that updates the graph structure during training. Extensive experiments on seven datasets demonstrate the superior performance of HypCSE.

  • Open Access

    Structural Information-based Hierarchical Diffusion for Offline Reinforcement Learning

    by Xianghua Zeng, Hao Peng, Angsheng Li, Yicheng Pan

    Diffusion-based generative methods have shown promising potential for modeling trajectories from offline reinforcement learning (RL) datasets, and hierarchical diffusion has been introduced to mitigate variance accumulation and computational challenges in long-horizon planning tasks. However, existing approaches typically assume a fixed two-layer diffusion hierarchy with a single predefined temporal scale, which limits adaptability to diverse downstream tasks and reduces flexibility in decision making. In this work, we propose SIHD, a novel Structural Information-based Hierarchical Diffusion framework for effective and stable offline policy learning in long-horizon environments with sparse rewards. Specifically, we analyze structural information embedded in offline trajectories to construct the diffusion hierarchy adaptively, enabling flexible trajectory modeling across multiple temporal scales. Rather than relying on reward predictions from localized sub-trajectories, we quantify the structural information gain of each state community and use it as a conditioning signal within the corresponding diffusion layer. To reduce overreliance on offline datasets, we introduce a structural entropy regularizer that encourages exploration of underrepresented states while avoiding extrapolation errors from distributional shifts. Extensive evaluations on challenging offline RL tasks show that SIHD significantly outperforms state-of-the-art baselines in decision-making performance and demonstrates superior generalization across diverse scenarios.

  • Open Access

    SetKE: Knowledge Editing for Knowledge Elements Overlap

    by Yifan Wei, Xiaoyan Yu, Ran Song, Hao Peng, Angsheng Li

    Large Language Models (LLMs) excel in tasks such as retrieval and question answering but require updates to incorporate new knowledge and reduce inaccuracies and hallucinations. Traditional updating methods, like fine-tuning and incremental learning, face challenges such as overfitting and high computational costs. Knowledge Editing (KE) provides a promising alternative but often overlooks the Knowledge Element Overlap (KEO) phenomenon, where multiple triplets share common elements, leading to editing conflicts. We identify the prevalence of KEO in existing KE datasets and show its significant impact on current KE methods, causing performance degradation in handling such triplets. To address this, we propose a new formulation, Knowledge Set Editing (KSE), and introduce SetKE, a method that edits sets of triplets simultaneously. Experimental results demonstrate that SetKE outperforms existing methods in KEO scenarios on mainstream LLMs. Additionally, we introduce EditSet, a dataset containing KEO triplets, providing a comprehensive benchmark.

  • Open Access

    A Survey of Structural Entropy: Theory, Methods, and Applications

    by Dingli Su, Hao Peng, Yicheng Pan, Angsheng Li

    Classical information theory, a cornerstone of artificial intelligence, is fundamentally limited by its local perspective, often analyzing pairwise interactions while ignoring the larger, hierarchical architecture of complex systems. Structural entropy (SE) presents a paradigm shift, extending Shannon entropy to quantify information on a global scale and measure the uncertainty embedded in a system's organizational hierarchy. Although its applications have broadened significantly from its origins in community detection across diverse AI domains, a systematic synthesis of its theory, computational methods, and applications is currently lacking. This survey provides a comprehensive overview of SE to fill this critical void in the literature. We offer a detailed examination of its theoretical foundations, computational frameworks, and key learning paradigms, with a focus on its integration with graph learning and reinforcement learning. Through an exploration of its diverse applications, we highlight the power of SE to advance graph-based analysis and modeling. Finally, we discuss key challenges and future research opportunities for incorporating SE principles into the development of more interpretable and theoretically grounded AI systems.


  • Open Access

    AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning

    by Yifan Wei, Xiaoyan Yu, Yixuan Weng, Tengfei Pan, Angsheng Li, Li Du

    Large Language Models (LLMs), when enhanced through reasoning-oriented post-training, evolve into powerful Large Reasoning Models (LRMs). Tool-Integrated Reasoning (TIR) further extends their capabilities by incorporating external tools, but existing methods often rely on rigid, predefined tool-use patterns that risk degrading core language competence. Inspired by the human ability to adaptively select tools, we introduce AutoTIR, a reinforcement learning framework that enables LLMs to autonomously decide whether and which tool to invoke during the reasoning process, rather than following static tool-use strategies. AutoTIR leverages a hybrid reward mechanism that jointly optimizes for task-specific answer correctness, structured output adherence, and penalization of incorrect tool usage, thereby encouraging both precise reasoning and efficient tool integration. Extensive evaluations across diverse knowledge-intensive, mathematical, and general language modeling tasks demonstrate that AutoTIR achieves superior overall performance, significantly outperforming baselines and exhibits superior generalization in tool-use behavior. These results highlight the promise of reinforcement learning in building truly generalizable and scalable TIR capabilities in LLMs. The code and data are available at https://github.com/weiyifan1023/AutoTIR.


  • Open Access

    Robustness Evaluation of Graph-based News Detection Using Network Structural Information

    by Xianghua Zeng, Hao Peng, Angsheng Li

    Although Graph Neural Networks (GNNs) have shown promising potential in fake news detection, they remain highly vulnerable to adversarial manipulations within social networks. Existing methods primarily establish connections between malicious accounts and individual target news to investigate the vulnerability of graph-based detectors, while they neglect the structural relationships surrounding targets, limiting their effectiveness in robustness evaluation. In this work, we propose a novel Structural Information principles-guided Adversarial Attack Framework, namely SI2AF, which effectively challenges graph-based detectors and further probes their detection robustness. Specifically, structural entropy is introduced to quantify the dynamic uncertainty in social engagements and identify hierarchical communities that encompass all user accounts and news posts. An influence metric is presented to measure each account's probability of engaging in random interactions, facilitating the design of multiple agents that manage distinct malicious accounts. For each target news, three attack strategies are developed through multi-agent collaboration within the associated subgraph to optimize evasion against black-box detectors. By incorporating the adversarial manipulations generated by SI2AF, we enrich the original network structure and refine graph-based detectors to improve their robustness against adversarial attacks. Extensive evaluations demonstrate that SI2AF significantly outperforms state-of-the-art baselines in attack effectiveness with an average improvement of 16.71%, and enhances GNN-based detection robustness by 41.54% on average.