Advanced Graph Neural Networks

Derniers papiers

• SemStruct: Contextualizing Semantic Embeddings with Structural Information for Schema Matching

  Inwon Kang, Kavitha Srinivas, Nandana Mihindukulasooriya, Sola Shirai, Parikshit Ram, Horst Samulowitz, Oshani Seneviratne · 1 juin 2026

  Schema matching is a fundamental step in integrating heterogeneous data sources. While Pre-trained Language Models (PLMs) have revolutionized this task by capturing linguistic semantics, they typically process tabular data as serialized text sequences of standalone column descriptions. This serializ…

• An Efficient and Scalable Graph Condensation with Structure-Preserving

  Yulin Hu, Fuyan Ou, Ye Yuan · 1 juin 2026

  Graph condensation (GC) is pivotal for enabling Graph Neural Networks (GNNs) deployment in resource-constrained scenarios by compressing large-scale graphs into compact synthetic counterparts. Existing GC methods commonly suffer from computational inefficiency due to coupled optimization as well as …

• AbstainGNN: Teaching Graph Neural Networks to Abstain for Graph Classification

  Xixun Lin, Zhiheng Zhou, Zhengyin Zhang, Yancheng Chen, Shuai Zhang, Ge Zhang, Shichao Zhu, Lixin Zou, Chuan Zhou, Peng Zhang, Shirui Pan, Yanan Cao · 1 juin 2026

  Graph classification is a core task in graph data mining with widespread real-world applications. Recent advances in graph neural networks (GNNs) have led to substantial performance improvements for graph classification. However, existing GNNs are typically forced to make predictions even under high…

• On Efficient Scaling of GNNs via IO-Aware Layers Implementations

  Daria Fomina, Daniil Krasylnikov, Alexey Boykov, Andrey Dolgovyazov, Vyacheslav Zhdanovskiy, Fedor Velikonivtsev · 1 juin 2026

  Graph Neural Networks (GNNs) are bottlenecked by sparse, irregular memory access. Popular frameworks such as DGL and PyTorch Geometric support general message passing, but complex layers often materialize edge-wise intermediates, increasing memory traffic and limiting scalability on large graphs. We…

• Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithms

  Xiang Wu, Rong-Hua Li, Xunkai Li, Kangfei Zhao, Hongchao Qin, Guoren Wang · 1 juin 2026

  Graph coarsening reduces the size of a graph while preserving certain properties. Most existing methods preserve either spectral or spatial characteristics. Recent research shows that topology-preserving coarsening methods maintain GNN performance on coarsened graphs but suffer from exponential time…

• DG-CoLearn: An Efficient Collaborative Learning Framework for Dynamic Graphs

  Ashley Hoi-Ting Au, Zikun Zhang, Ligang He, Qiang Ni · 1 juin 2026

  Dynamic graph learning (DGL) is essential for modelling evolving graph data, but existing methods suffer from significant computational overhead due to repeated full-snapshot retraining and are not well-suited for collaborative settings with partitioned data. In realistic graph systems, cross-partit…

• From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves

  Haritz Puerto, Haonan Li, Xudong Han, Timothy Baldwin, Iryna Gurevych · 1 juin 2026

  Large reasoning models (LRMs) produce reasoning traces (RTs) that often contain sensitive information. These leaky thoughts are difficult to control and frequently violate explicit privacy directives. Because RTs can be exposed through prompt injection attacks, this becomes a direct privacy risk to …

• DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers

  Shraman Pal, Can Li · 1 juin 2026

  Many learning tasks in science and engineering are characterized by sparse datasets, which limits the effectiveness of purely data-driven approaches. At the same time, these problems are often accompanied by rich domain knowledge derived from physical laws, operational requirements, and expert heuri…

• Graphical einops: bridging tensor networks and computation graphs

  Vincent Wang-Ma\'scianica, Nikhil Khatri · 1 juin 2026

  Architecture diagrams are ubiquitous in deep learning, but they are usually only representational: the tensor-program identities they suggest are still proved by prose and tensor-axis manipulation. We introduce a formal graphical calculus for the structural fragment of tensor programming underlying …

• Structural Bias Beyond Homophily: A Study of Fairness in Link Prediction

  Lilian Marey, Mathilde Perez, Tiphaine Viard, Charlotte Laclau · 1 juin 2026

  Graph link prediction (LP) plays a critical role in socially impactful applications such as job recommendation and friendship formation, making fairness a critical concern in this task. While many fairness-aware methods manipulate graph structures to mitigate prediction disparities, the topological …

• Graph Neural Networks Are Not Continuous Across Graph Resolutions

  Christian Koke, Yuesong Shen, Abhishek Saroha, Marvin Eisenberger, Bastian Rieck, Michael Bronstein, Daniel Cremers · 1 juin 2026

  We show that contrary to conventional wisdom in the community, graph neural networks (GNNs) are not continuous with respect to all natural modes of graph convergence. As a result, GNNs may generate substantially different latent representations for graphs that are very similar. In particular they as…

• Scaling Higher-Order Graph Learning with Maximal Clique Complexes

  Antoine Vialle, Aref Einizade, Fragkiskos D. Malliaros, Jhony H. Giraldo · 1 juin 2026

  Graph neural networks (GNNs) are limited to modeling pairwise interactions, while higher-order models based on cell complexes achieve greater expressivity but often suffer from poor scalability. We introduce simplified and factored cellular Weisfeiler Leman tests (sCWL and fCWL), which preserve the …

• Reading Between the Citations: A Typed Claim Network for Scientific Literature

  Ning Ding, Sergio J. Rodr\'iguez M\'endez, Pouya G. Omran · 1 juin 2026

  Knowledge graphs over corpora of inter-referencing documents - scholarly papers, legal opinions, policy briefs - encode the topology of reference but not its stance. The standard representation collapses a rich evaluative relation into an untyped edge, losing the very content that supports community…

• Post-Training Neural Network Pruning using Graph Curvature

  Shuhang Tan, Jayson Sia, Paul Bogdan, Radoslav Ivanov · 1 juin 2026

  This paper provides a fresh view of the neural network (NN) pruning problem through the lens of graph theory. To achieve effective pruning, we aim to identify the main NN data flows and the corresponding NN connections that are most and least important for the performance of the full model. Unlike t…

• GraphARC: A Comprehensive Benchmark for Graph-Based Abstract Reasoning

  Saku Peltonen, August B{\o}gh R{\o}nberg, Andreas Plesner, Roger Wattenhofer · 1 juin 2026

  Relational reasoning lies at the heart of intelligence, but existing benchmarks are typically confined to formats such as grids or text. We introduce GraphARC, a benchmark for abstract reasoning on graph-structured data. GraphARC generalizes the few-shot transformation learning paradigm of the Abstr…

• Graph Machine Learning in the Era of Large Language Models (LLMs)

  Shijie Wang, Jiani Huang, Zhikai Chen, Yu Song, Wenzhuo Tang, Haitao Mao, Wenqi Fan, Hui Liu, Xiaorui Liu, Dawei Yin, Qing Li · 1 juin 2026

  Graphs play an important role in representing complex relationships in various domains like social networks, knowledge graphs, and molecular discovery. With the advent of deep learning, Graph Neural Networks (GNNs) have emerged as a cornerstone in Graph Machine Learning (Graph ML), facilitating the …

• View Space: Learning Representation across Arbitrary Graphs

  Dooho Lee, Myeong Kong, Minho Jeong, Jaemin Yoo · 1 juin 2026

  Generalizing pretrained models to unseen datasets without retraining is a central challenge toward foundation models. Achieving fully inductive inference on numerical data is particularly difficult due to large variations in feature dimensionality and semantics across datasets. We observe that, in t…

• Generating Graph-like Rules for Knowledge Graph Reasoning via Diffusion Models

  Haoxiang Cheng, Yunfei Wang, Chao Chen, Kewei Cheng, Zhipeng Lin, Haoxuan Li, Changjun Fan, Shixuan Liu · 1 juin 2026

  Logical rules constitute a cornerstone of knowledge graph (KG) reasoning, valued for their interpretability and ability to model relational patterns. However, existing rule mining methods predominantly focus on simple chain-like rules and therefore neglect the richer relational information encoded i…

• Better Later Than Sooner: Neuro-Symbolic Knowledge Graph Construction via Ontology-grounded Post-extraction Correction

  Lorenzo Loconte, Timothy Hospedales, Cristina Cornelio · 29 mai 2026

  Question answering (QA) is a core challenge in AI, particularly for complex queries requiring multi-hop reasoning across documents, or symbolic operations like aggregation or exhaustive listing. Retrieval-augmented generation has become the dominant approach to QA, with recent graph-based variants a…

• When Do Graph Foundation Models Transfer? A Data-Centric Theory

  Jiajun Zhu, Ying Chen, Peihao Wang, Yixuan He, Pan Li, Aditya Akella, Zhangyang Wang · 29 mai 2026

  Graph foundation models (GFMs) aim to reuse a single backbone across diverse graph domains, yet their transfer is often uneven and can exhibit negative transfer. While most prior work improves transfer through architectural or adaptation choices, we ask a data-centric question: which properties of t…

• SAHG: Sector-Anisotropic Hyperbolic Graph Model for Social Bot Detection

  Hanning Lu, Yingguang Yang, Jinwei Su, Yang Liu, Zhaoqian Yao, Yaoming Li, Taoran Liang, Ziyi Zhang, Ran Ran, Kefu Xu, Bin Chong · 29 mai 2026

  LLM-driven social bots can generate fluent, human-like text, reducing the discriminative advantage of content-based detection alone. However, coordinated campaigns still leave relational patterns -- interactions, behavioral similarity, shared neighborhoods, community positions, and coordinated activ…

• Rubric-Guided Process Reward for Stepwise Model Routing

  Shenghao Ye, Yu Guo, Zhengheng Li, Shuangwu Chen, Jian Yang · 29 mai 2026

  Stepwise model routing improves the efficiency of Large Reasoning Models (LRMs) by assigning each reasoning step to a suitable model. Recent methods formulate routing as a sequential decision process and train the router with reinforcement learning. However, although they model routing as a process,…

• What drives performance in molecular MPNNs? An operator-level factorial benchmark

  Panyu Jiao, Shuizhou Chen, Yiheng Shen, Yuyang Wang, Runhai Ouyang, Wei Xie · 29 mai 2026

  Message-passing neural networks (MPNNs) are widely used for molecular property prediction, but their deployment as monolithic architectures makes it difficult to identify how specific message-passing operators affect performance. We present an operator-level factorial benchmark that decomposes 2D mo…

• mcp-proto-okn: Natural-language access to open scientific knowledge graphs through the Model Context Protocol

  Peter W. Rose, Benjamin M. Good, Amanda M. Saravia-Butler, Charlotte A. Nelson, James P. Balhoff, Yaphet Kebede, Patricia L. Whetzel, Christopher Bizon, Andrew I. Su, Sergio E. Baranzini · 29 mai 2026

  MCP Server Proto-OKN (mcp-proto-okn) is a Python-based Model Context Protocol server that enables AI assistants to discover, inspect, query and integrate scientific knowledge graphs through natural language. The server provides graph routing, schema inspection, SPARQL execution, ontology expansion, …

• Gated Graph Attention Networks with Learnable Temperature

  Zhongtian Ma, Hao Wu, Yexin Zhang, Qiaosheng Zhang, Zhen Wang · 29 mai 2026

  Graph attention networks learn neighbor importance through data-dependent coefficients, but standard layers lack explicit control over unreliable feature dimensions and use fixed sharpness of attention coefficient distributions. This paper proposes gated graph attention and learnable temperature for…