Advanced Graph Neural Networks

Latest papers

• When Trees Are Not Enough: Learning Mixed-Topology Feature Graphs with Adaptive Graph Sparse Autoencoders

  Xiaozuo Shen, Yifei Cai, Tian Tan, Rui Ning, Chunsheng Xin, Hongyi Wu · 1 October 2026

  Sparse autoencoders (SAEs) expose interpretable features in large language model activations, yet existing structured SAEs impose single-parent trees or forests, while post-hoc graphs permit multiple parents but neither guide feature learning nor ensure reliable relation recovery. We introduce the A…

• Equivariant Sheaf Neural Networks: Learning Geometric Transport on Graphs

  Alessio Borgi, Mario Severino, Fabrizio Silvestri, Pietro Li\`o · 1 October 2026

  Equivariant graph neural networks provide a principled way to model geometric systems, but efficient first-order architectures remain limited in how vector information can be transformed as it moves across a graph. We introduce \textsc{ESNN}, an Equivariant Sheaf Neural Network that enriches this in…

• GraphCert: Bootstrap Agentic Graph Reasoning with Certified Evidence Rubrics

  Weiqi Jiang, Yuchen Ying, Rui Wang, Kaixuan Chen, Bingde Hu, Shunyu Liu, Yu Wang, Tongya Zheng · 1 October 2026

  Graph agents extend large language models (LLMs) with the ability to actively explore and reason over knowledge graphs through multi-step interactions with graph tools. However, training capable graph agents typically requires large collections of question-answer pairs and reasoning trajectories, wh…

• HM-ROUTER: Joint Model and Harness Routing for Agentic Systems

  Hao Mark Chen, Royson Lee, Yasuyuki Okoshi, Dimitris Anastasiou, Wayne Luk, Hongxiang Fan · 30 September 2026

  Agent performance depends on both the underlying model and the harness that manages its tool use and execution. Selecting a suitable pair requires accounting for their compatibility, yet training samples may cover only a subset of the growing combination space. We introduce HM-Router, a routing meth…

• Dagger: Decoupling-based Model Stealing Attack against Graph Neural Networks

  Ying Song, Xiaowei Jia, Balaji Palanisamy · 30 September 2026

  As Graph Neural Networks (GNNs) are widely deployed as Machine Learning-as-a-Service (MLaaS) APIs, model stealing attacks have emerged as a critical security threat. By querying a victim model's black-box API, an adversary can construct a functionally equivalent surrogate model, compromising proprie…

• GARDiff: Graph-Aligned Residual Diffusion for Probabilistic Multivariate Time-Series Forecasting

  Rui Han, Min Yang, Xu Zhang, Xinghao Yang, Wei Liu, Yongshun Gong · 30 September 2026

  Diffusion models have recently shown strong potential for probabilistic multivariate time-series forecasting by modeling complex conditional distributions. Recent decoupled diffusion frameworks further separate forecasting into deterministic prediction and stochastic residual generation, making it n…

• Measuring trainable degrees of freedom in materials graph neural networks: a random-subspace intrinsic dimension analysis

  Shehroz Ahmad Shoaib, Kangming Li · 30 September 2026

  Final predictive accuracy is the standard basis for comparing graph neural networks (GNNs) in materials-property prediction, but it does not show how strongly performance depends on access to trainable parameter-space directions. Here, we introduce trainable-degree dependence as a complementary char…

• ImbalancE: Inference-Time Latent Search Against Degree Imbalance in Link Prediction

  Alberto Bernardi, Luca Costabello, Christophe Gueret · 30 September 2026

  Knowledge Graph Embedding models have been extensively used to learn representations of entities and relations in Knowledge Graphs for predicting missing links. However, the quality of the learned representations varies a lot across different areas of the graph. If previous research has loosely link…

• WorldGraph: Graph-Native World Modeling

  Zezhong Ding, Yipeng Li, Xike Xie · 29 September 2026

  World models infer latent states of an environment to capture its underlying dynamics and predict future evolution. Many real-world environments, however, are inherently relational and observed as evolving graphs, where entities, relations, and their properties change over time. Prior graph-related …

• HARMONIA: Interpretable Graph Learning through Mixtures of Neural Bases

  Quan D. Bui, Nguyen Do, An Nguyen Dang, Huyen Nguyen, Nhu Duc Minh Nguyen, My T. Thai · 29 September 2026

  Existing interpretable graph additive models still face limitations in either computational scalability or modeling flexibility. In terms of structural modeling, previous approaches either face quadratic scaling costs or sacrifice explicit source-to-target contribution decomposition. In terms of fea…

• Beyond Fixed Features: Architecture-Dependent Sensitivity to Node Representations under Heterophily

  Priyanath Maji, Sidharth Gaur, Rajavinoth Paul Durai · 29 September 2026

  Graph Neural Networks (GNNs) perform well on homophilic graphs but struggle in heterophilic settings, where connected nodes often carry dissimilar labels. Existing evaluations typically compare architectures under a fixed node-feature representation, leaving unclear whether conclusions about heterop…

• Investigating the Effect of k-NN Preprocessing on Developing Graph Neural Networks: A Fairness-Based Perspective

  Nikolaos Zafeiropoulos, Emmanouil Mavrikos, George E. Tsekouras · 29 September 2026

  In this paper, a methodology to design fair graph convolutional neural networks (GCNs) is developed and tested over several application data sets. The graphs that are used as inputs to the network are constructed by a k-nearest neighbor-based preprocessing procedure, while fairness issues are consid…

• AutoHGNN: Robust and Efficient Neural Architecture Search for Hypergraph Neural Networks

  Sirui Li, Pietro Li\`o b, Xinsheng Li, Baisong Liu, Chengbin Peng · 29 September 2026

  Hypergraph neural networks have achieved significant success in recent years. However, manual architecture crafting is labor-intensive and often fails to capture complex, higher-order relations, making the automation of hypergraph neural network structure design crucial. To improve the automation an…

• ZeroGAR: Benchmarking the Adversarial Robustness of Zero-Shot Graph Models

  Zhongjian Zhang, Xiao Wang, Busheng Zhang, Bo Yan, Xingtong Yu, Yue Gao, Jia Li, Chuan Shi · 29 September 2026

  Zero-shot graph models (ZGMs), which learn transferable knowledge from source graphs and directly apply to unseen target graphs without any adaptation, have achieved promising performance and attracted considerable attention. Despite their proliferation, existing ZGMs are predominantly evaluated on …

• TwinS-GCN: Spectral conjugate for Spectral Graph Convolutional Networks

  Chun Hei Michael Chan, Flavia Petruso, Dimitri Van De Ville · 29 September 2026

  Graph convolutional networks propagate information by repeated local aggregation through a graph shift operator; i.e., a $K$-layer network reaches $K$ hops neighborhood. On the one hand, such spreading can lead to oversmoothing. On the other hand, long-range dependencies demand the depth. Transporti…

• Transfer Learning for Edge Classification on Dynamic Text-Attributed Graphs

  Tyler Bonnet, Marek Rei · 29 September 2026

  Learning transferable representations for dynamic text-attributed graphs (DyTAGs) requires models to capture underlying interaction dynamics that persist across domains. However, existing methods tend to overfit to domain-specific structural, temporal, and semantic patterns, limiting edge classifica…

• Spectral Reversal: Counteracting Singular Value Bias for Graph Prompting

  Hanxu Yang, Yuhuan Zhao, Xiaodong He, Zhao Kang · 29 September 2026

  Pre-training Graph Neural Networks (GNNs) via self-supervised learning has become a dominant paradigm, yet efficiently adapting frozen encoders remains a challenge. Graph prompting offers a parameter-efficient alternative to fine-tuning, but existing methods largely treat pre-trained models as opaqu…

• From Phase Transition to Systemic Failure: A Decoupled Analytics Framework for GNN Robustness

  Shuai Yan, Dan Peng, Jie Li, Ke Wang · 29 September 2026

  Data quality is a major bottleneck for the reliable deployment of graph neural networks (GNNs) in real-world graph mining tasks. Among various sources of degradation, label noise and feature distribution shift (hereafter referred to as distribution shift) are two common yet fundamentally different c…

• Scaffold: Support Graph Theory Based Sparsification for Graph Neural Networks

  Siddhartha Shankar Das, Sai Karthik Navuluru, S M Ferdous, Ryan A. Rossi, Baris Coskunuzer, Lakshman Tamil, Edoardo Serra, Alex Pothen, Robert Rallo, Mahantesh M Halappanavar · 28 September 2026

  Graph neural networks (GNNs) rely on message passing over graph edges, making their computational and memory costs strongly dependent on graph density. Graph sparsification offers a natural way to reduce these costs, but removing edges indiscriminately can distort important communication structure a…

• Robust Graph Clustering Network for Multiple Missing Data

  Keyuan Qiu, Renda Han, Zhen Tang, Qiang He, Xingwei Wang, Wenxin Zhang, Guangzhen Yao, Junxin Chen, Qingjian Ni · 28 September 2026

  Clustering on graphs where both node attributes and structural links are partially missing remains a challenging task. Existing methods typically rely on imputation-then-clustering on single-view missingness incomplete graphs, which are vulnerable to cross-view error propagation and cluster-boundary…

• Adaptive Interaction Graphs for Particle Simulation

  Aiden Zhou · 28 September 2026

  Learned particle simulators based on graph neural networks achieve strong one-step accuracy, but errors compound over long horizons. An underexplored variable is the interaction graph: existing methods fix its topology via k-nearest neighbors or a static radius rule, regardless of local model confid…

• Fixed Points Without Fixed Diffusion: Implicit Neural Sheaves for Convergent Test-Time Computation

  R\'emi Bourgerie, \v{S}ar\={u}nas Girdzijauskas, Viktoria Fodor · 28 September 2026

  Implicit Graph Neural Networks (IGNNs) define node representations as fixed points of message-passing operators, enabling effectively infinite-depth propagation, iteration-independent parameterization, and flexible test-time computation. Yet these benefits depend on the equilibrium being unique and …

• Training Graph Foundation Models on The Web Graph

  Ryoma Sato · 28 September 2026

  We introduce Acacia, a graph foundation model, trained on the web graph. Acacia (i) supports arbitrary feature dimensionalities and semantics without additional training, (ii) supports a wide range of tasks, including node classification, link prediction, node clustering, and graph generation, witho…

• ICE: Task-Aligned Clifford Latent Fields for Multimodal Graph Foundation Models

  Xunkai Li, Xu Wang, Yinlin Zhu, Xiong Yongfu, Yi Liu, Rong-Hua Li, Guoren Wang · 25 September 2026

  Multimodal attributed graphs connect entities, visual content, language, and observed relations. Learning one foundation across such graphs requires more than compressing each node into a fused Euclidean vector. The representation must preserve entity semantics, construct interaction state from grap…

• Effective Graph and Rank-based Contextual Embeddings for Textual and Multimedia Data

  Thiago C\'esar Castilho Almeida, Gustavo Rosseto Let\'icio, Lucas Pascotti Valem, Andr\'e Freitas, Daniel Carlos Guimar\~aes Pedronette · 25 September 2026

  In a data-driven world, efficiently organizing and mapping relationships between objects is crucial. Graphs are powerful tools for modeling these connections, being widely used in social networks, telecommunications, and biology. However, graph-based methods often face high computational costs, part…