Advanced Graph Neural Networks

Derniers papiers

• Variational Bayesian Flow Network for Graph Generation

  Yida Xiong, Jiameng Chen, Xiuwen Gong, Jia Wu, Shirui Pan, Wenbin Hu · 2 février 2026

  Graph generation aims to sample discrete node and edge attributes while satisfying coupled structural constraints. Diffusion models for graphs often adopt largely factorized forward-noising, and many flow-matching methods start from factorized reference noise and coordinate-wise interpolation, so no…

• Helios: A Foundational Language Model for Smart Energy Knowledge Reasoning and Application

  Haoyu Jiang, Fanjie Zeng, Boan Qu, Xiaojie Lin, Wei Zhong · 2 février 2026

  In the global drive toward carbon neutrality, deeply coordinated smart energy systems underpin industrial transformation. However, the interdisciplinary, fragmented, and fast-evolving expertise in this domain prevents general-purpose LLMs, which lack domain knowledge and physical-constraint awarenes…

• FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks

  Naen Xu, Jinghuai Zhang, Ping He, Chunyi Zhou, Jun Wang, Zhihui Fu, Tianyu Du, Zhaoxiang Wang, Shouling Ji · 2 février 2026

  Large language models (LLMs) have been widely integrated into critical automated workflows, including contract review and job application processes. However, LLMs are susceptible to manipulation by fraudulent information, which can lead to harmful outcomes. Although advanced defense methods have bee…

• MM-OpenFGL: A Comprehensive Benchmark for Multimodal Federated Graph Learning

  Xunkai Li, Yuming Ai, Yinlin Zhu, Haodong Lu, Yi Zhang, Guohao Fu, Bowen Fan, Qiangqiang Dai, Rong-Hua Li, Guoren Wang · 2 février 2026

  Multimodal-attributed graphs (MMAGs) provide a unified framework for modeling complex relational data by integrating heterogeneous modalities with graph structures. While centralized learning has shown promising performance, MMAGs in real-world applications are often distributed across isolated plat…

• Sequence Diffusion Model for Temporal Link Prediction in Continuous-Time Dynamic Graph

  Nguyen Minh Duc, Viet Cuong Ta · 2 février 2026

  Temporal link prediction in dynamic graphs is a fundamental problem in many real-world systems. Existing temporal graph neural networks mainly focus on learning representations of historical interactions. Despite their strong performance, these models are still purely discriminative, producing point…

• Aligning the Unseen in Attributed Graphs: Interplay between Graph Geometry and Node Attributes Manifold

  Aldric Labarthe (CB, UNIGE), Roland Bouffanais (UNIGE), Julien Randon-Furling (CB) · 2 février 2026

  The standard approach to representation learning on attributed graphs -- i.e., simultaneously reconstructing node attributes and graph structure -- is geometrically flawed, as it merges two potentially incompatible metric spaces. This forces a destructive alignment that erodes information about the …

• Graph is a Substrate Across Data Modalities

  Ziming Li, Xiaoming Wu, Zehong Wang, Jiazheng Li, Yijun Tian, Jinhe Bi, Yunpu Ma, Yanfang Ye, Chuxu Zhang · 2 février 2026

  Graphs provide a natural representation of relational structure that arises across diverse domains. Despite this ubiquity, graph structure is typically learned in a modality- and task-isolated manner, where graph representations are constructed within individual task contexts and discarded thereafte…

• Temporal Graph Pattern Machine

  Yijun Ma, Zehong Wang, Weixiang Sun, Yanfang Ye · 2 février 2026

  Temporal graph learning is pivotal for deciphering dynamic systems, where the core challenge lies in explicitly modeling the underlying evolving patterns that govern network transformation. However, prevailing methods are predominantly task-centric and rely on restrictive assumptions -- such as shor…

• Learning to Execute Graph Algorithms Exactly with Graph Neural Networks

  Muhammad Fetrat Qharabagh, Artur Back de Luca, George Giapitzakis, Kimon Fountoulakis · 2 février 2026

  Understanding what graph neural networks can learn, especially their ability to learn to execute algorithms, remains a central theoretical challenge. In this work, we prove exact learnability results for graph algorithms under bounded-degree and finite-precision constraints. Our approach follows a t…

• Influence Functions for Edge Edits in Non-Convex Graph Neural Networks

  Jaeseung Heo, Kyeongheung Yun, Seokwon Yoon, MoonJeong Park, Jungseul Ok, Dongwoo Kim · 2 février 2026

  Understanding how individual edges influence the behavior of graph neural networks (GNNs) is essential for improving their interpretability and robustness. Graph influence functions have emerged as promising tools to efficiently estimate the effects of edge deletions without retraining. However, exi…

• Full-Graph vs. Mini-Batch Training: Comprehensive Analysis from a Batch Size and Fan-Out Size Perspective

  Mengfan Liu, Da Zheng, Junwei Su, Chuan Wu · 2 février 2026

  Full-graph and mini-batch Graph Neural Network (GNN) training approaches have distinct system design demands, making it crucial to choose the appropriate approach to develop. A core challenge in comparing these two GNN training approaches lies in characterizing their model performance (i.e., converg…

• Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning

  Arvind Mahankali, Kaiyue Wen, Tengyu Ma · 2 février 2026

  Long chain-of-thought reasoning (Long CoT) is now fundamental to state-of-the-art LLMs, especially in mathematical reasoning. However, LLM generation is highly sequential, and long CoTs lead to a high latency. We propose to train Divide-and-Conquer CoT (DC-CoT) to reduce the latency. With DC-CoT, th…

• Graph Attention Network for Node Regression on Random Geometric Graphs with Erd\H{o}s--R\'enyi contamination

  Somak Laha, Suqi Liu, Morgane Austern · 2 février 2026

  Graph attention networks (GATs) are widely used and often appear robust to noise in node covariates and edges, yet rigorous statistical guarantees demonstrating a provable advantage of GATs over non-attention graph neural networks~(GNNs) are scarce. We partially address this gap for node regression …

• Heterogeneous Graph Alignment for Joint Reasoning and Interpretability

  Zahra Moslemi, Ziyi Liang, Norbert Fortin, Babak Shahbaba · 2 février 2026

  Multi-graph learning is crucial for extracting meaningful signals from collections of heterogeneous graphs. However, effectively integrating information across graphs with differing topologies, scales, and semantics, often in the absence of shared node identities, remains a significant challenge. We…

• Scalable Topology-Preserving Graph Coarsening with Graph Collapse

  Xiang Wu, Rong-Hua Li, Xunkai Li, Kangfei Zhao, Hongchao Qin, Guoren Wang · 2 février 2026

  Graph coarsening reduces the size of a graph while preserving certain properties. Most existing methods preserve either spectral or spatial characteristics. Recent research has shown that preserving topological features helps maintain the predictive performance of graph neural networks (GNNs) traine…

• Learn More with Less: Uncertainty Consistency Guided Query Selection for RLVR

  Hao Yi, Yulan Hu, Xin Li, Sheng Ouyang, Lizhong Ding, Yong Liu · 2 février 2026

  Large Language Models (LLMs) have recently improved mathematical reasoning through Reinforcement Learning with Verifiable Reward (RLVR). However, existing RLVR algorithms require large query budgets, making annotation costly. We investigate whether fewer but more informative queries can yield simila…

• CoDCL: Counterfactual Data Augmentation Contrastive Learning for Continuous-Time Dynamic Network Link Prediction

  Hantong Feng, Yonggang Wu, Duxin Chen, Wenwu Yu · 2 février 2026

  The rapid growth and continuous structural evolution of dynamic networks make effective predictions increasingly challenging. To enable prediction models to adapt to complex temporal environments, they need to be robust to emerging structural changes. We propose a dynamic network learning framework …

• JAF: Judge Agent Forest

  Sahil Garg, Brad Cheezum, Sridhar Dutta, Vishal Agarwal · 2 février 2026

  Judge agents are fundamental to agentic AI frameworks: they provide automated evaluation, and enable iterative self-refinement of reasoning processes. We introduce JAF: Judge Agent Forest, a framework in which the judge agent conducts joint inference across a cohort of query--response pairs generate…

• NAG: A Unified Native Architecture for Encoder-free Text-Graph Modeling in Language Models

  Haisong Gong, Zhibo Liu, Qiang Liu, Shu Wu, Liang Wang · 2 février 2026

  Prevailing methods for integrating graphs into Language Models (LMs) typically rely on a segregated architecture: external Graph Neural Networks (GNNs) encode structural topology, while LMs process textual semantics. We argue this approach is suboptimal for text-graphs: it creates a conceptually dis…

• Adaptive Edge Learning for Density-Aware Graph Generation

  Seyedeh Ava Razi Razavi, James Sargant, Sheridan Houghten, Renata Dividino · 2 février 2026

  Generating realistic graph-structured data is challenging due to discrete structures, variable sizes, and class-specific connectivity patterns that resist conventional generative modelling. While recent graph generation methods employ generative adversarial network (GAN) frameworks to handle permuta…

• Enhancing Logical Expressiveness in Graph Neural Networks via Path-Neighbor Aggregation

  Han Yu, Xiaojuan Zhao, Aiping Li, Kai Chen, Ziniu Liu, Zhichao Peng · 2 février 2026

  Graph neural networks (GNNs) can effectively model structural information of graphs, making them widely used in knowledge graph (KG) reasoning. However, existing studies on the expressive power of GNNs mainly focuses on simple single-relation graphs, and there is still insufficient discussion on the…

• How Expressive Are Graph Neural Networks in the Presence of Node Identifiers?

  Arie Soeteman, Michael Benedikt, Martin Grohe, Balder ten Cate · 30 janvier 2026

  Graph neural networks (GNNs) are a widely used class of machine learning models for graph-structured data, based on local aggregation over neighbors. GNNs have close connections to logic. In particular, their expressive power is linked to that of modal logics and bounded-variable logics with countin…

• Towards Anomaly-Aware Pre-Training and Fine-Tuning for Graph Anomaly Detection

  Yunhui Liu, Jiashun Cheng, Yiqing Lin, Qizhuo Xie, Jia Li, Fugee Tsung, Hongzhi Yin, Tao Zheng, Jianhua Zhao, Tieke He · 30 janvier 2026

  Graph anomaly detection (GAD) has garnered increasing attention in recent years, yet remains challenging due to two key factors: (1) label scarcity stemming from the high cost of annotations and (2) homophily disparity at node and class levels. In this paper, we introduce Anomaly-Aware Pre-Training …

• Metric Graph Kernels via the Tropical Torelli Map

  Yueqi Cao, Anthea Monod · 30 janvier 2026

  We introduce the first graph kernels for metric graphs via tropical algebraic geometry. In contrast to conventional graph kernels based on graph combinatorics such as nodes, edges, and subgraphs, our metric graph kernels are purely based on the geometry and topology of the underlying metric space. A…

• Bridging Graph Structure and Knowledge-Guided Editing for Interpretable Temporal Knowledge Graph Reasoning

  Shiqi Fan, Quanming Yao, Hongyi Nie, Wentao Ma, Zhen Wang, Wen Hua · 30 janvier 2026

  Temporal knowledge graph reasoning (TKGR) aims to predict future events by inferring missing entities with dynamic knowledge structures. Existing LLM-based reasoning methods prioritize contextual over structural relations, struggling to extract relevant subgraphs from dynamic graphs. This limits str…