Advanced Graph Neural Networks

Derniers papiers

• MoEEdit: Efficient and Routing-Stable Knowledge Editing for Mixture-of-Experts LLMs

  Yupu Gu, Rongzhe Wei, Andy Zhu, Pan Li · 12 février 2026

  Knowledge editing (KE) enables precise modifications to factual content in large language models (LLMs). Existing KE methods are largely designed for dense architectures, limiting their applicability to the increasingly prevalent sparse Mixture-of-Experts (MoE) models that underpin modern scalable L…

• Colorful Talks with Graphs: Human-Interpretable Graph Encodings for Large Language Models

  Angelo Zangari, Peyman Baghershahi, Sourav Medya · 12 février 2026

  Graph problems are fundamentally challenging for large language models (LLMs). While LLMs excel at processing unstructured text, graph tasks require reasoning over explicit structure, permutation invariance, and computationally complex relationships, creating a mismatch with the representations of t…

• Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain Adaptation

  Wei Chen, Xingyu Guo, Shuang Li, Zhao Zhang, Yan Zhong, Fuzhen Zhuang, Deqing wang · 12 février 2026

  Graph Domain Adaptation (GDA) transfers knowledge from labeled source graphs to unlabeled target graphs but is challenged by complex, multi-faceted distributional shifts. Existing methods attempt to reduce distributional shifts by aligning manually selected graph elements (e.g., node attributes or s…

• SynergyKGC: Reconciling Topological Heterogeneity in Knowledge Graph Completion via Topology-Aware Synergy

  Xuecheng Zou, Yu Tang, Bingbing Wang · 12 février 2026

  Knowledge Graph Completion (KGC) fundamentally hinges on the coherent fusion of pre-trained entity semantics with heterogeneous topological structures to facilitate robust relational reasoning. However, existing paradigms encounter a critical "structural resolution mismatch," failing to reconcile di…

• Interpretable Graph-Level Anomaly Detection via Contrast with Normal Prototypes

  Qiuran Zhao, Kai Ming Ting, Xinpeng Li · 12 février 2026

  The task of graph-level anomaly detection (GLAD) is to identify anomalous graphs that deviate significantly from the majority of graphs in a dataset. While deep GLAD methods have shown promising performance, their black-box nature limits their reliability and deployment in real-world applications. A…

• Towards Autonomous Mathematics Research

  Tony Feng (Maggie), Trieu H. Trinh (Maggie), Garrett Bingham (Maggie), Dawsen Hwang (Maggie), Yuri Chervonyi (Maggie), Junehyuk Jung (Maggie), Joonkyung Lee (Maggie), Carlo Pagano (Maggie), Sang-hyun Kim (Maggie), Federico Pasqualotto (Maggie), Sergei Gukov (Maggie), Jonathan N. Lee (Maggie), Junsu Kim (Maggie), Kaiying Hou (Maggie), Golnaz Ghiasi (Maggie), Yi Tay (Maggie), YaGuang Li (Maggie), Chenkai Kuang (Maggie), Yuan Liu (Maggie), Hanzhao (Maggie), Lin, Evan Zheran Liu, Nigamaa Nayakanti, Xiaomeng Yang, Heng-tze Cheng, Demis Hassabis, Koray Kavukcuoglu, Quoc V. Le, Thang Luong · 12 février 2026

  Recent advances in foundational models have yielded reasoning systems capable of achieving a gold-medal standard at the International Mathematical Olympiad. The transition from competition-level problem-solving to professional research, however, requires navigating vast literature and constructing l…

• MOTGNN: Interpretable Graph Neural Networks for Multi-Omics Disease Classification

  Tiantian Yang, Zhiqian Chen · 12 février 2026

  Integrating multi-omics data, such as DNA methylation, mRNA expression, and microRNA (miRNA) expression, offers a comprehensive view of the biological mechanisms underlying disease. However, the high dimensionality of multi-omics data, the heterogeneity across modalities, and the lack of reliable bi…

• Exploring the impact of adaptive rewiring in Graph Neural Networks

  Charlotte Cambier van Nooten, Christos Aronis, Yuliya Shapovalova, Lucia Cavallaro · 12 février 2026

  This paper explores sparsification methods as a form of regularization in Graph Neural Networks (GNNs) to address high memory usage and computational costs in large-scale graph applications. Using techniques from Network Science and Machine Learning, including Erd\H{o}s-R\'enyi for model sparsificat…

• How Much Reasoning Do Retrieval-Augmented Models Add beyond LLMs? A Benchmarking Framework for Multi-Hop Inference over Hybrid Knowledge

  Junhong Lin, Bing Zhang, Song Wang, Ziyan Liu, Dan Gutfreund, Julian Shun, Yada Zhu · 12 février 2026

  Large language models (LLMs) continue to struggle with knowledge-intensive questions that require up-to-date information and multi-hop reasoning. Augmenting LLMs with hybrid external knowledge, such as unstructured text and structured knowledge graphs, offers a promising alternative to costly contin…

• RiemannGL: Riemannian Geometry Changes Graph Deep Learning

  Li Sun, Qiqi Wan, Suyang Zhou, Zhenhao Huang, Philip S. Yu · 12 février 2026

  Graphs are ubiquitous, and learning on graphs has become a cornerstone in artificial intelligence and data mining communities. Unlike pixel grids in images or sequential structures in language, graphs exhibit a typical non-Euclidean structure with complex interactions among the objects. This paper a…

• Efficient Learning on Large Graphs using a Densifying Regularity Lemma

  Jonathan Kouchly, Ben Finkelshtein, Michael Bronstein, Ron Levie · 12 février 2026

  Learning on large graphs presents significant challenges, with traditional Message Passing Neural Networks suffering from computational and memory costs scaling linearly with the number of edges. We introduce the Intersecting Block Graph (IBG), a low-rank factorization of large directed graphs based…

• Predictive AI with External Knowledge Infusion: Datasets and Benchmarks for Stock Markets

  Ambedkar Dukkipati, Kawin Mayilvaghanan, Naveen Kumar Pallekonda, Sai Prakash Hadnoor, Ranga Shaarad Ayyagari · 12 février 2026

  Fluctuations in stock prices are influenced by a complex interplay of factors that go beyond mere historical data. These factors, themselves influenced by external forces, encompass inter-stock dynamics, broader economic factors, various government policy decisions, outbreaks of wars, etc. Furthermo…

• Learning Structure-Semantic Evolution Trajectories for Graph Domain Adaptation

  Wei Chen, Xingyu Guo, Shuang Li, Yan Zhong, Zhao Zhang, Fuzhen Zhuang, Hongrui Liu, Libang Zhang, Guo Ye, Huimei He · 12 février 2026

  Graph Domain Adaptation (GDA) aims to bridge distribution shifts between domains by transferring knowledge from well-labeled source graphs to given unlabeled target graphs. One promising recent approach addresses graph transfer by discretizing the adaptation process, typically through the constructi…

• Proficient Graph Neural Network Design by Accumulating Knowledge on Large Language Models

  Jialiang Wang, Hanmo Liu, Shimin Di, Zhili Wang, Jiachuan Wang, Lei Chen, Xiaofang Zhou · 12 février 2026

  High-level automation is increasingly critical in AI, driven by rapid advances in large language models (LLMs) and AI agents. However, LLMs, despite their general reasoning power, struggle significantly in specialized, data-sensitive tasks such as designing Graph Neural Networks (GNNs). This difficu…

• Exact Subgraph Isomorphism Network with Mixed $L_{0,2}$ Norm Constraint for Predictive Graph Mining

  Taiga Kojima, Haruto Kajita, Ayato Kohara, Masayuki Karasuyama · 11 février 2026

  In the graph-level prediction task (predict a label for a given graph), the information contained in subgraphs of the input graph plays a key role. In this paper, we propose Exact subgraph Isomorphism Network (EIN), which combines the exact subgraph enumeration, a neural network, and a sparse regula…

• Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesics

  Zhichen Zeng, Ruizhong Qiu, Wenxuan Bao, Tianxin Wei, Xiao Lin, Yuchen Yan, Tarek F. Abdelzaher, Jiawei Han, Hanghang Tong · 11 février 2026

  Graph neural networks, despite their impressive performance, are highly vulnerable to distribution shifts on graphs. Existing graph domain adaptation (graph DA) methods often implicitly assume a mild shift between source and target graphs, limiting their applicability to real-world scenarios with la…

• Enhanced Graph Transformer with Serialized Graph Tokens

  Ruixiang Wang, Yuyang Hong, Shiming Xiang, Chunhong Pan · 11 février 2026

  Transformers have demonstrated success in graph learning, particularly for node-level tasks. However, existing methods encounter an information bottleneck when generating graph-level representations. The prevalent single token paradigm fails to fully leverage the inherent strength of self-attention …

• Position: Message-passing and spectral GNNs are two sides of the same coin

  Antonis Vasileiou, Juan Cervino, Pascal Frossard, Charilaos I. Kanatsoulis, Christopher Morris, Michael T. Schaub, Pierre Vandergheynst, Zhiyang Wang, Guy Wolf, Ron Levie · 11 février 2026

  Graph neural networks (GNNs) are commonly divided into message-passing neural networks (MPNNs) and spectral graph neural networks, reflecting two largely separate research traditions in machine learning and signal processing. This paper argues that this divide is mostly artificial, hindering progres…

• Differentiable Tripartite Modularity for Clustering Heterogeneous Graphs

  Beno\^it Hurpeau · 11 février 2026

  Clustering heterogeneous relational data remains a central challenge in graph learning, particularly when interactions involve more than two types of entities. While differentiable modularity objectives such as DMoN have enabled end-to-end community detection on homogeneous and bipartite graphs, ext…

• Generalizing GNNs with Tokenized Mixture of Experts

  Xiaoguang Guo, Zehong Wang, Jiazheng Li, Shawn Spitzel, Qi Yang, Kaize Ding, Jundong Li, Chuxu Zhang · 11 février 2026

  Deployed graph neural networks (GNNs) are frozen at deployment yet must fit clean data, generalize under distribution shifts, and remain stable to perturbations. We show that static inference induces a fundamental tradeoff: improving stability requires reducing reliance on shift-sensitive features, …

• BRAVA-GNN: Betweenness Ranking Approximation Via Degree MAss Inspired Graph Neural Network

  Justin Dachille, Aurora Rossi, Sunil Kumar Maurya, Frederik Mallmann-Trenn, Xin Liu, Fr\'ed\'eric Giroire, Tsuyoshi Murata, Emanuele Natale · 11 février 2026

  Computing node importance in networks is a long-standing fundamental problem that has driven extensive study of various centrality measures. A particularly well-known centrality measure is betweenness centrality, which becomes computationally prohibitive on large-scale networks. Graph Neural Network…

• Step-resolved data attribution for looped transformers

  Georgios Kaissis, David Mildenberger, Juan Felipe Gomez, Martin J. Menten, Eleni Triantafillou · 11 février 2026

  We study how individual training examples shape the internal computation of looped transformers, where a shared block is applied for $\tau$ recurrent iterations to enable latent reasoning. Existing training-data influence estimators such as TracIn yield a single scalar score that aggregates over all…

• Scaling GraphLLM with Bilevel-Optimized Sparse Querying

  Yangzhe Peng, Haiquan Qiu, Quanming Yao, Kun He · 11 février 2026

  LLMs have recently shown strong potential in enhancing node-level tasks on text-attributed graphs (TAGs) by providing explanation features. However, their practical use is severely limited by the high computational and monetary cost of repeated LLM queries. To illustrate, naively generating explanat…

• Importance inversion transfer identifies shared principles for cross-domain learning

  Daniele Caligiore · 11 février 2026

  The capacity to transfer knowledge across scientific domains relies on shared organizational principles. However, existing transfer-learning methodologies often fail to bridge radically heterogeneous systems, particularly under severe data scarcity or stochastic noise. This study formalizes Explaina…

• Circuit Fingerprints: How Answer Tokens Encode Their Geometrical Path

  Andres Saurez, Neha Sengar, Dongsoo Har · 11 février 2026

  Circuit discovery and activation steering in transformers have developed as separate research threads, yet both operate on the same representational space. Are they two views of the same underlying structure? We show they follow a single geometric principle: answer tokens, processed in isolation, en…