Advanced Graph Neural Networks

Derniers papiers

• Towards Understanding and Avoiding Limitations of Convolutions on Graphs

  Andreas Roth · 5 février 2026

  While message-passing neural networks (MPNNs) have shown promising results, their real-world impact remains limited. Although various limitations have been identified, their theoretical foundations remain poorly understood, leading to fragmented research efforts. In this thesis, we provide an in-dep…

• Billion-Scale Graph Foundation Models

  Maya Bechler-Speicher, Yoel Gottlieb, Andrey Isakov, David Abensur, Ami Tavory, Daniel Haimovich, Ido Guy, Udi Weinsberg · 5 février 2026

  Graph-structured data underpins many critical applications. While foundation models have transformed language and vision via large-scale pretraining and lightweight adaptation, extending this paradigm to general, real-world graphs is challenging. In this work, we present Graph Billion- Foundation-Fu…

• Are Graph Attention Networks Able to Model Structural Information?

  Farshad Noravesh, Reza Haffari, Layki Soon, Arghya Pal · 5 février 2026

  Graph Attention Networks (GATs) have emerged as powerful models for learning expressive representations from such data by adaptively weighting neighboring nodes through attention mechanisms. However, most existing approaches primarily rely on node attributes and direct neighborhood connections, ofte…

• Toward Effective Multimodal Graph Foundation Model: A Divide-and-Conquer Based Approach

  Sicheng Liu, Xunkai Li, Daohan Su, Ru Zhang, Hongchao Qin, Ronghua Li, Guoren Wang · 5 février 2026

  Graph Foundation Models (GFMs) have achieved remarkable success in generalizing across diverse domains. However, they mainly focus on Text-Attributed Graphs (TAGs), leaving Multimodal-Attributed Graphs (MAGs) largely untapped. Developing Multimodal Graph Foundation Models (MGFMs) allows for leveragi…

• Early-Exit Graph Neural Networks

  Andrea Giuseppe Di Francesco, Maria Sofia Bucarelli, Franco Maria Nardini, Raffaele Perego, Nicola Tonellotto, Fabrizio Silvestri · 5 février 2026

  Early-exit mechanisms allow deep neural networks to stop inference once prediction confidence is high, reducing latency and energy on easy inputs while retaining full-depth accuracy on harder ones. Similarly, adding early exit mechanisms to Graph Neural Networks (GNNs), the go-to models for graph-st…

• Training A Foundation Model to Represent Graphs as Vectors

  Qi Feng, Jicong Fan · 5 février 2026

  This paper aims to train a graph foundation model that is able to represent any graph as a vector preserving structural and semantic information useful for downstream graph-level tasks such as graph classification and graph clustering. To learn the features of graphs from diverse domains while maint…

• Generalized Schr\"odinger Bridge on Graphs

  Panagiotis Theodoropoulos, Juno Nam, Evangelos Theodorou, Jaemoo Choi · 5 février 2026

  Transportation on graphs is a fundamental challenge across many domains, where decisions must respect topological and operational constraints. Despite the need for actionable policies, existing graph-transport methods lack this expressivity. They rely on restrictive assumptions, fail to generalize a…

• WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning

  Zelai Xu, Zhexuan Xu, Ruize Zhang, Chunyang Zhu, Shi Yu, Weilin Liu, Quanlu Zhang, Wenbo Ding, Chao Yu, Yu Wang · 5 février 2026

  Recent advancements in Large Language Models (LLMs) have largely focused on depth scaling, where a single agent solves long-horizon problems with multi-turn reasoning and tool use. However, as tasks grow broader, the key bottleneck shifts from individual competence to organizational capability. In t…

• Discrete Diffusion-Based Model-Level Explanation of Heterogeneous GNNs with Node Features

  Pallabee Das, Stefan Heindorf · 5 février 2026

  Many real-world datasets, such as citation networks, social networks, and molecular structures, are naturally represented as heterogeneous graphs, where nodes belong to different types and have additional features. For example, in a citation network, nodes representing "Paper" or "Author" may includ…

• Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs

  Kiran Tomlinson, Tobias Schnabel, Adith Swaminathan, Jennifer Neville · 4 février 2026

  Inference-time scaling via chain-of-thought (CoT) reasoning is a major driver of state-of-the-art LLM performance, but it comes with substantial latency and compute costs. We address a fundamental theoretical question: how many reasoning tokens are required to solve a problem as input size grows? By…

• Enhancing Imbalanced Node Classification via Curriculum-Guided Feature Learning and Three-Stage Attention Network

  Abdul Joseph Fofanah, Lian Wen, David Chen, Shaoyang Zhang · 4 février 2026

  Imbalanced node classification in graph neural networks (GNNs) happens when some labels are much more common than others, which causes the model to learn unfairly and perform badly on the less common classes. To solve this problem, we propose a Curriculum-Guided Feature Learning and Three-Stage Atte…

• GASTON: Graph-Aware Social Transformer for Online Networks

  Olha Wloch, Liam Hebert, Robin Cohen, Lukasz Golab · 4 février 2026

  Online communities have become essential places for socialization and support, yet they also possess toxicity, echo chambers, and misinformation. Detecting this harmful content is difficult because the meaning of an online interaction stems from both what is written (textual content) and where it is…

• SPGCL: Simple yet Powerful Graph Contrastive Learning via SVD-Guided Structural Perturbation

  Hao Deng, Zhang Guo, Shuiping Gou, Bo Liu · 4 février 2026

  Graph Neural Networks (GNNs) are sensitive to structural noise from adversarial attacks or imperfections. Existing graph contrastive learning (GCL) methods typically rely on either random perturbations (e.g., edge dropping) for diversity or spectral augmentations (e.g., SVD) to preserve structural p…

• Manifold Random Features

  Ananya Parashar, Derek Long, Dwaipayan Saha, Krzysztof Choromanski · 4 février 2026

  We present a new paradigm for creating random features to approximate bi-variate functions (in particular, kernels) defined on general manifolds. This new mechanism of Manifold Random Features (MRFs) leverages discretization of the manifold and the recently introduced technique of Graph Random Featu…

• Generator-based Graph Generation via Heat Diffusion

  Anthony Stephenson, Ian Gallagher, Christopher Nemeth · 4 février 2026

  Graph generative modelling has become an essential task due to the wide range of applications in chemistry, biology, social networks, and knowledge representation. In this work, we propose a novel framework for generating graphs by adapting the Generator Matching (arXiv:2410.20587) paradigm to graph…

• Data-Driven Graph Filters via Adaptive Spectral Shaping

  Dylan Sandfelder, Mihai Cucuringu, Xiaowen Dong · 4 février 2026

  We introduce Adaptive Spectral Shaping, a data-driven framework for graph filtering that learns a reusable baseline spectral kernel and modulates it with a small set of Gaussian factors. The resulting multi-peak, multi-scale responses allocate energy to heterogeneous regions of the Laplacian spectru…

• Exploring the Global-to-Local Attention Scheme in Graph Transformers: An Empirical Study

  Gang Wu, Zhengwei Wang · 4 février 2026

  Graph Transformers (GTs) show considerable potential in graph representation learning. The architecture of GTs typically integrates Graph Neural Networks (GNNs) with global attention mechanisms either in parallel or as a precursor to attention mechanisms, yielding a local-and-global or local-to-glob…

• RPG-AE: Neuro-Symbolic Graph Autoencoders with Rare Pattern Mining for Provenance-Based Anomaly Detection

  Asif Tauhid, Sidahmed Benabderrahmane, Mohamad Altrabulsi, Ahamed Foisal, Talal Rahwan · 4 février 2026

  Advanced Persistent Threats (APTs) are sophisticated, long-term cyberattacks that are difficult to detect because they operate stealthily and often blend into normal system behavior. This paper presents a neuro-symbolic anomaly detection framework that combines a Graph Autoencoder (GAE) with rare pa…

• Topology Matters: A Cautionary Case Study of Graph SSL on Neuro-Inspired Benchmarks

  May Kristine Jonson Carlon, Su Myat Noe, Haojiong Wang, Yasuo Kuniyoshi · 4 février 2026

  Understanding how local interactions give rise to global brain organization requires models that can represent information across multiple scales. We introduce a hierarchical self-supervised learning (SSL) framework that jointly learns node-, edge-, and graph-level embeddings, inspired by multimodal…

• Deep Graph Learning will stall without Network Science

  Christopher Bl\"ocker, Martin Rosvall, Ingo Scholtes, Jevin D. West · 4 février 2026

  Deep graph learning focuses on flexible and generalizable models that learn patterns in an automated fashion. Network science focuses on models and measures revealing the organizational principles of complex systems with explicit assumptions. Both fields share the same goal: to better model and unde…

• GraphDancer: Training LLMs to Explore and Reason over Graphs via Curriculum Reinforcement Learning

  Yuyang Bai, Zhuofeng Li, Ping Nie, Jianwen Xie, Yu Zhang · 4 février 2026

  Large language models (LLMs) increasingly rely on external knowledge to improve factuality, yet many real-world knowledge sources are organized as heterogeneous graphs rather than plain text. Reasoning over such graph-structured knowledge poses two key challenges: (1) navigating structured, schema-d…

• Tabula RASA: Exposing and Breaking the Relational Bottleneck in Transformers

  Jonas Petersen, Camilla Mazzoleni, Riccardo Maggioni · 4 février 2026

  Transformers achieve remarkable performance across many domains, yet struggle with tasks requiring multi-hop relational reasoning over structured data. We analyze this limitation through circuit complexity: standard transformers are $\mathsf{TC}^0$-complete and require $\Omega(k)$ layers for $k$-hop…

• Entropy-Guided Dynamic Tokens for Graph-LLM Alignment in Molecular Understanding

  Zihao Jing, Qiuhao Zeng, Ruiyi Fang, Yan Sun, Boyu Wang, Pingzhao Hu · 4 février 2026

  Molecular understanding is central to advancing areas such as scientific discovery, yet Large Language Models (LLMs) struggle to understand molecular graphs effectively. Existing graph-LLM bridges often adapt the Q-Former-style connector with fixed-length static tokens, which is originally designed …

• GraDE: A Graph Diffusion Estimator for Frequent Subgraph Discovery in Neural Architectures

  Yikang Yang, Zhengxin Yang, Minghao Luo, Luzhou Peng, Hongxiao Li, Wanling Gao, Lei Wang, Jianfeng Zhan · 4 février 2026

  Finding frequently occurring subgraph patterns or network motifs in neural architectures is crucial for optimizing efficiency, accelerating design, and uncovering structural insights. However, as the subgraph size increases, enumeration-based methods are perfectly accurate but computationally prohib…

• Breaking the Static Graph: Context-Aware Traversal for Robust Retrieval-Augmented Generation

  Kwun Hang Lau, Fangyuan Zhang, Boyu Ruan, Yingli Zhou, Qintian Guo, Ruiyuan Zhang, Xiaofang Zhou · 3 février 2026

  Recent advances in Retrieval-Augmented Generation (RAG) have shifted from simple vector similarity to structure-aware approaches like HippoRAG, which leverage Knowledge Graphs (KGs) and Personalized PageRank (PPR) to capture multi-hop dependencies. However, these methods suffer from a "Static Graph …