Advanced Graph Neural Networks

Derniers papiers

• Accelerate Vector Diffusion Maps by Landmarks

  Sing-Yuan Yeh, Yi-An Wu, Hau-Tieng Wu, Mao-Pei Tsui · 24 mars 2026

  We propose a landmark-constrained algorithm, LA-VDM (Landmark Accelerated Vector Diffusion Maps), to accelerate the Vector Diffusion Maps (VDM) framework built upon the Graph Connection Laplacian (GCL), which captures pairwise connection relationships within complex datasets. LA-VDM introduces a nov…

• Unified-MAS: Universally Generating Domain-Specific Nodes for Empowering Automatic Multi-Agent Systems

  Hehai Lin, Yu Yan, Zixuan Wang, Bo Xu, Sudong Wang, Weiquan Huang, Ruochen Zhao, Minzhi Li, Chengwei Qin · 24 mars 2026

  Automatic Multi-Agent Systems (MAS) generation has emerged as a promising paradigm for solving complex reasoning tasks. However, existing frameworks are fundamentally bottlenecked when applied to knowledge-intensive domains (e.g., healthcare and law). They either rely on a static library of general …

• Thinking Deeper, Not Longer: Depth-Recurrent Transformers for Compositional Generalization

  Hung-Hsuan Chen · 24 mars 2026

  Standard Transformers have a fixed computational depth, fundamentally limiting their ability to generalize to tasks requiring variable-depth reasoning, such as multi-hop graph traversal or nested logic. We propose a depth-recurrent Transformer that decouples computational depth from parameter count …

• Reasoning Topology Matters: Network-of-Thought for Complex Reasoning Tasks

  Fan Huang · 24 mars 2026

  Existing prompting paradigms structure LLM reasoning in limited topologies: Chain-of-Thought (CoT) produces linear traces, while Tree-of-Thought (ToT) performs branching search. Yet complex reasoning often requires merging intermediate results, revisiting hypotheses, and integrating evidence from mu…

• From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context

  Peyman Baghershahi, Gregoire Fournier, Pranav Nyati, Sourav Medya · 24 mars 2026

  Graph Neural Networks (GNNs) have emerged as powerful tools for learning over structured data, including text-attributed graphs (TAGs), which are common in domains such as citation networks, social platforms, and knowledge graphs. GNNs are not inherently interpretable and thus, many explanation meth…

• LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs

  Xiaoxu Ma, Dong Li, Minglai Shao, Xintao Wu, Chen Zhao · 24 mars 2026

  Text-attributed graphs, where nodes are enriched with textual attributes, have become a powerful tool for modeling real-world networks such as citation, social, and transaction networks. However, existing methods for learning from these graphs often assume that the distributions of training and test…

• Adversarial Attacks on Locally Private Graph Neural Networks

  Matta Varun (Indian Institute of Technology Kharagpur, India), Ajay Kumar Dhakar (Indian Institute of Technology Kharagpur, India), Yuan Hong (University of Connecticut, USA), Shamik Sural (Indian Institute of Technology Kharagpur, India) · 24 mars 2026

  Graph neural network (GNN) is a powerful tool for analyzing graph-structured data. However, their vulnerability to adversarial attacks raises serious concerns, especially when dealing with sensitive information. Local Differential Privacy (LDP) offers a privacy-preserving framework for training GNNs…

• Riemannian Geometry Speaks Louder Than Words: From Graph Foundation Model to Next-Generation Graph Intelligence

  Philip S. Yu, Li Sun · 24 mars 2026

  Graphs provide a natural description of the complex relationships among objects, and play a pivotal role in communications, transportation, social computing, the life sciences, etc. Currently, there is strong agreement that Graph Foundation Models (GFMs) are essential for advancing graph learning, y…

• Graph of States: Solving Abductive Tasks with Large Language Models

  Yu Luo, Rongchen Gao, Lu Teng, Xidao Wen, Jiamin Jiang, Qingliang Zhang, Yongqian Sun, Shenglin Zhang, Jiasong Feng, Tong Liu, Wenjie Zhang, Dan Pei · 24 mars 2026

  Logical reasoning encompasses deduction, induction, and abduction. However, while Large Language Models (LLMs) have effectively mastered the former two, abductive reasoning remains significantly underexplored. Existing frameworks, predominantly designed for static deductive tasks, fail to generalize…

• Sharper Generalization Bounds for Transformer

  Yawen Li, Tao Hu, Zhouhui Lian, Wan Tian, Yijie Peng, Huiming Zhang, Zhongyi Li · 24 mars 2026

  This paper studies generalization error bounds for Transformer models. Based on the offset Rademacher complexity, we derive sharper generalization bounds for different Transformer architectures, including single-layer single-head, single-layer multi-head, and multi-layer Transformers. We first expre…

• Graph-Aware Text-Only Backdoor Poisoning for Text-Attributed Graphs

  Qi Luo, Minghui Xu, Dongxiao Yu, Xiuzhen Cheng · 24 mars 2026

  Many learning systems now use graph data in which each node also contains text, such as papers with abstracts or users with posts. Because these texts often come from open platforms, an attacker may be able to quietly poison a small part of the training data and later make the model produce wrong pr…

• A Hierarchical Error-Corrective Graph Framework for Autonomous Agents with LLM-Based Action Generation

  Cong Cao, Jingyao Zhang, Kun Tong · 24 mars 2026

  We propose a Hierarchical Error-Corrective Graph FrameworkforAutonomousAgentswithLLM-BasedActionGeneration(HECG),whichincorporates three core innovations: (1) Multi-Dimensional Transferable Strategy (MDTS): by integrating task quality metrics (Q), confidence/cost metrics (C), reward metrics (R), and…

• Beyond the Academic Monoculture: A Unified Framework and Industrial Perspective for Attributed Graph Clustering

  Yunhui Liu, Yue Liu, Yongchao Liu, Tao Zheng, Stan Z. Li, Xinwang Liu, Tieke He · 24 mars 2026

  Attributed Graph Clustering (AGC) is a fundamental unsupervised task that partitions nodes into cohesive groups by jointly modeling structural topology and node attributes. While the advent of graph neural networks and self-supervised learning has catalyzed a proliferation of AGC methodologies, a wi…

• KG-Hopper: Empowering Compact Open LLMs with Knowledge Graph Reasoning via Reinforcement Learning

  Shuai Wang, Yinan Yu · 24 mars 2026

  Large Language Models (LLMs) demonstrate impressive natural language capabilities but often struggle with knowledge-intensive reasoning tasks. Knowledge Base Question Answering (KBQA), which leverages structured Knowledge Graphs (KGs) exemplifies this challenge due to the need for accurate multi-hop…

• Can LLMs Fool Graph Learning? Exploring Universal Adversarial Attacks on Text-Attributed Graphs

  Zihui Chen, Yuling Wang, Pengfei Jiao, Kai Wu, Xiao Wang, Xiang Ao, Dalin Zhang · 24 mars 2026

  Text-attributed graphs (TAGs) enhance graph learning by integrating rich textual semantics and topological context for each node. While boosting expressiveness, they also expose new vulnerabilities in graph learning through text-based adversarial surfaces. Recent advances leverage diverse backbones,…

• Integrating Meta-Features with Knowledge Graph Embeddings for Meta-Learning

  Antonis Klironomos, Ioannis Dasoulas, Francesco Periti, Mohamed Gad-Elrab, Heiko Paulheim, Anastasia Dimou, Evgeny Kharlamov · 23 mars 2026

  The vast collection of machine learning records available on the web presents a significant opportunity for meta-learning, where past experiments are leveraged to improve performance. Two crucial meta-learning tasks are pipeline performance estimation (PPE), which predicts pipeline performance on ta…

• GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems

  Hongjiang Chen, Xin Zheng, Yixin Liu, Pengfei Jiao, Shiyuan Li, Huan Liu, Zhidong Zhao, Ziqi Xu, Ibrahim Khalil, Shirui Pan · 23 mars 2026

  Large language model (LLM)-based multi-agent systems (MAS) have demonstrated exceptional capabilities in solving complex tasks, yet their effectiveness depends heavily on the underlying communication topology that coordinates agent interactions. Within these systems, successful problem-solving often…

• Graph-Informed Adversarial Modeling: Infimal Subadditivity of Interpolative Divergences

  Panagiota Birmpa (Heriot--Watt University, Maxwell Institute for Mathematical Sciences), Eric Joseph Hall (Heriot--Watt University, Maxwell Institute for Mathematical Sciences) · 23 mars 2026

  We study adversarial learning when the target distribution factorizes according to a known Bayesian network. For interpolative divergences, including $(f,\Gamma)$-divergences, we prove a new infimal subadditivity principle showing that, under suitable conditions, a global variational discrepancy is …

• Exploring Subnetwork Interactions in Heterogeneous Brain Network via Prior-Informed Graph Learning

  Siyu Liu, Guangqi Wen, Peng Cao, Jinzhu Yang, Xiaoli Liu, Fei Wang, Osmar R. Zaiane · 23 mars 2026

  Modeling the complex interactions among functional subnetworks is crucial for the diagnosis of mental disorders and the identification of functional pathways. However, learning the interactions of the underlying subnetworks remains a significant challenge for existing Transformer-based methods due t…

• DIAL-KG: Schema-Free Incremental Knowledge Graph Construction via Dynamic Schema Induction and Evolution-Intent Assessment

  Weidong Bao, Yilin Wang, Ruyu Gao, Fangling Leng, Yubin Bao, Ge Yu · 23 mars 2026

  Knowledge Graphs (KGs) are foundational to applications such as search, question answering, and recommendation. Conventional knowledge graph construction methods are predominantly static, rely ing on a single-step construction from a fixed corpus with a prede f ined schema. However, such methods are…

• Scalable Prompt Routing via Fine-Grained Latent Task Discovery

  Yunyi Zhang, Soji Adeshina, Patrick Guan, Ashwin Ganesh, Zhen Han, Vassilis N. Ioannidis, Huzefa Rangwala, George Karypis · 23 mars 2026

  Prompt routing dynamically selects the most appropriate large language model from a pool of candidates for each query, optimizing performance while managing costs. As model pools scale to include dozens of frontier models with narrow performance gaps, existing approaches face significant challenges:…

• Stochastic Sequential Decision Making over Expanding Networks with Graph Filtering

  Zhan Gao, Bishwadeep Das, Elvin Isufi · 23 mars 2026

  Graph filters leverage topological information to process networked data with existing methods mainly studying fixed graphs, ignoring that graphs often expand as nodes continually attach with an unknown pattern. The latter requires developing filter-based decision-making paradigms that take evolutio…

• Any-Subgroup Equivariant Networks via Symmetry Breaking

  Abhinav Goel, Derek Lim, Hannah Lawrence, Stefanie Jegelka, Ningyuan Huang · 23 mars 2026

  The inclusion of symmetries as an inductive bias, known as equivariance, often improves generalization on geometric data (e.g. grids, sets, and graphs). However, equivariant architectures are usually highly constrained, designed for symmetries chosen a priori, and not applicable to datasets with oth…

• Subspace Projection Methods for Fast Spectral Embeddings of Evolving Graphs

  Mohammad Eini, Abdullah Karaaslanli, Vassilis Kalantzis, Panagiotis A. Traganitis · 23 mars 2026

  Several graph data mining, signal processing, and machine learning downstream tasks rely on information related to the eigenvectors of the associated adjacency or Laplacian matrix. Classical eigendecomposition methods are powerful when the matrix remains static but cannot be applied to problems wher…

• Position: Spectral GNNs Are Neither Spectral Nor Superior for Node Classification

  Qin Jiang, Chengjia Wang, Michael Lones, Dongdong Chen, Wei Pang · 20 mars 2026

  Spectral Graph Neural Networks (Spectral GNNs) for node classification promise frequency-domain filtering on graphs, yet rest on flawed foundations. Recent work shows that graph Laplacian eigenvectors do not in general have the key properties of a true Fourier basis, but leaves the empirical success…