Advanced Graph Neural Networks

Derniers papiers

• Gradual Capacity Growth for Sparse Network Discovery

  Qihang Yao, Constantine Dovrolis · 23 juin 2026

  Sparse neural network methods typically assume that the target sparsity (or density) is fixed in advance, even though the relationship between network capacity and performance is generally unknown and task-dependent. Existing approaches (including iterative pruning, dynamic sparse training, and prun…

• CQD-SHAP: Explainable Complex Query Answering via Shapley Values

  Parsa Abbasi, Stefan Heindorf · 23 juin 2026

  Complex query answering (CQA) goes beyond the widely studied link prediction task by addressing more sophisticated queries that require multi-hop reasoning over incomplete knowledge graphs (KGs). Research on neural and neurosymbolic CQA methods is still an emerging field. Almost all of these methods…

• Collapsed Effective Operators for Higher-order Structures

  Maximilian Krahn, Lennart Bastian, Vikas Garg, Bj\"orn Schuller, Tolga Birdal · 23 juin 2026

  Higher-order structures are powerful relational modeling tools, yet existing spectral operators decompose the topology into separate ranks, leaving practitioners to fuse the information back to vertices through ad hoc choices. We introduce Collapsed Effective Operators, which condense higher-order d…

• Revealing the Pitfalls and Re-Evaluating the Advancement of Heterophilic Graph Learning

  Sitao Luan, Qincheng Lu, Chenqing Hua, Xinyu Wang, Jiaqi Zhu, Xiao-Wen Chang · 23 juin 2026

  Over the past decade, Graph Neural Networks (GNNs) have achieved great success on machine learning tasks with relational data. However, recent studies have found that heterophily can cause significant performance degradation of GNNs, especially on node-level tasks. Numerous heterophilic benchmark da…

• Learning Graphs through Continuous Information Entropy Fields

  Hui Cong, Bo Sun, Ziheng Jiao, Yisheng An · 23 juin 2026

  Graph theory is inherently descriptive, capturing what relationships exist but not why they arise, because it treats edges as primitive constructs. This paper proposes a new explanatory framework for graph learning, where relationships emerge from latent continuous information entropy fields, and a …

• All Routes Lead to Collapse

  K. R. Balasubramanian · 23 juin 2026

  Attention sinks, representation collapse, and norm stratification are treated as transformer-specific pathologies. We show they are not specific to attention: they are what content-based routing does under a fixed similarity metric. We give a reframing identity: softmax attention is Boltzmann-weight…

• GRADE: Graph Representation of LLM Agent Dependency and Execution

  Yue Zhao · 23 juin 2026

  Can one graph represent every kind of LLM agent's run? A trace records what each step did, never what it relied on, the state it read, and the results it reused. GRADE recovers that missing layer: it models any run as one graph over its step nodes with two edge layers, execution edges (what ran in w…

• Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation

  Junshu Sun, Wanxing Chang, Qingming Huang, Shuhui Wang · 23 juin 2026

  Graph neural networks (GNNs) tightly couple their input-output parameters to dataset-specific feature spaces and target sets, exhibiting limited transferability across different datasets. In contrast, language models (LMs) generalize flexibly via a unified input-output interface, motivating recent a…

• A Spectral Theory of Normalized Corrected GNN Propagation

  Qihan Chen, Wei Li, Meng Qin, Jianfeng Hou · 23 juin 2026

  We develop a spectral theory for \emph{normalized corrected GNN propagation}. The object of study is the symmetric normalized adjacency with its degree-stationary component removed, matching the normalization used by standard GCN-style models while isolating the stationary direction most directly ti…

• Memory Is No Longer a Bottleneck: Memory-Efficient Graph Filtering for Scalable Collaborative Filtering

  Jin-Duk Park, Won-Yong Shin · 23 juin 2026

  Graph convolutional networks (GCNs) have demonstrated significant success in capturing complex user-item relationships for collaborative filtering (CF). However, due to their reliance on extensive model training, training-free graph filtering (GF)-based CF methods have emerged as a promising alterna…

• Universal Encoders for Modular Relational Deep Learning

  Jakub Pele\v{s}ka, Gustav \v{S}\'ir · 23 juin 2026

  Relational Deep Learning (RDL) models multi-tabular databases as temporal heterogeneous graphs for end-to-end representation learning. While RDL is evolving rapidly, existing approaches face significant generalization obstacles. They are either schema-specific, requiring training from scratch for ev…

• Causally Fair Node Classification on Non-IID Graph Data

  Yucong Dai, Lu Zhang, Yaowei Hu, Susan Gauch, Yongkai Wu · 23 juin 2026

  Fair machine learning seeks to identify and mitigate biases in predictions against unfavorable populations characterized by demographic attributes, such as race and gender. Recent research has extended fairness to graph data, such as social networks, but many studies neglect the causal relationships…

• PEAR: Permutation-Equivariant Adaptive Routing Multi-Agent Debate

  Yang Feng, Ziwei Xu, Xia Hu, Fengxiang He · 23 juin 2026

  Multi-agent debate improves the reliability of large language models (LLMs) through iterative peer critiques. However, fixed topologies often introduce persistent positional biases, amplify unreliable agents, and cause high sensitivity to role assignments. We introduce \textit{Permutation-Equivarian…

• Bridge the Gaps: Heterogeneous Attributed Graph Clustering via Quaternion Representation Learning

  Xinxi Chen, Junyang Chen, Yiqun Zhang, Chuangming Qiu, Xiang Zhang · 23 juin 2026

  Attributed graph clustering partitions nodes by jointly exploiting node attributes and graph topology. It remains challenging due to attribute heterogeneity and representation degradation during graph learning. Real-world datasets often contain heterogeneous attributes, i.e., numerical and categoric…

• TTFT-Aware Graph Chain-of-Thought:Distance-Indexed Neural A* for Low-Hallucination Multi-Hop Medical Reasoning

  Bechir Dardouri, Ka\"is Zhioua, Yassine Msaddak · 23 juin 2026

  Hallucinations and opaque reasoning remain unacceptable failure modes for clinical LLMs. We present a production-grade GraphRAG stack that constrains answers to verifiable graph chain-of-thought paths in a heterogeneous, ~700K-node medical knowledge graph powering a fertility assistant. The core ide…

• Adaptive Recurrent Message Passing for Test Time Computing on Graphs

  Junshu Sun, Wanxing Chang, Qingming Huang, Shuhui Wang · 23 juin 2026

  Pre-trained foundation models have demonstrated remarkable success in many domains, enabling a unified backbone to generalize across diverse downstream tasks. However, extending this paradigm to graph learning remains challenging due to the intrinsic mismatch between graph data and fixed architectur…

• Rethinking Molecular Graph Backdoors under Chemistry-aware Admission

  Thinh T. H. Nguyen, Sze Jue Yang, Khoa D. Doan, Chee Seng Chan, Kok-Seng Wong · 23 juin 2026

  Backdoor attacks on molecular graph neural networks (GNNs) are typically evaluated as abstract graph edits, but real molecular learning pipelines do not train on arbitrary graphs. Molecular records must first survive parsing, sanitization, canonicalization, and graph-string consistency checks. We fo…

• Multigrid Training for Molecular Generation using Graph Neural Networks

  Zixuan Ling, Paula Mercurio, Di Liu · 23 juin 2026

  Deep learning has demonstrated significant success for modeling biochemical molecular systems, where inputs are commonly represented as graphs or 3D grids. A major challenge is that computational cost scales with resolution, making full graph/grid computation of molecular densities expensive and oft…

• MMGNN: Multi-level, multi-color graph neural networks for molecular property prediction

  Trung Nguyen, Duc Duy Nguyen · 23 juin 2026

  Molecular message-passing neural networks commonly propagate chemically diverse interactions through a single graph, which may mix interaction-specific signals and require deep propagation to capture long-range effects. We introduce the Multi-level, Multi-color Graph Neural Network (MMGNN), a hierar…

• A Completion-Aware Framework for Impactful Counterfactual Explainability in Graph Neural Networks

  Maria Myrto Villia, Filippos Gouidis, Theodore Patkos, Panos Trahanias · 23 juin 2026

  In this study, we propose a novel pipeline for generic, model-agnostic, local-level counterfactual explainability in graph neural networks (GNNs). Although counterfactual explainers capable of both adding and removing edges have emerged in recent years, the need for generic and efficient solutions r…

• Ramanujan Graph Rewiring with Non Negative Resistance Curvature

  Hugo Attali, Rachid El Jouhri · 23 juin 2026

  Graph Neural Networks (GNNs) have emerged as a powerful paradigm for learning on graph-structured data by iteratively propagating and aggregating information across edges. However, conventional message passing schemes often suffer from over-squashing, whereby exponentially large neighborhoods are co…

• Breaking chains with trees: Deep learning with $\mathcal{O}(\log N)$ parallel time complexity

  Neeraj Mohan Sushma, Aditya Nagarsekar, Cabrel Teguemne Fokam, Robin Schiewer, Amit Kumar Pal, Anand Subramoney, David Kappel · 23 juin 2026

  Modern deep neural network architectures are trained via backpropagation, which requires errors to be sequentially propagated through all layers before parameters can be updated. This introduces two limitations: locking, where layer-wise updates are strictly interdependent and cannot proceed in para…

• Repeated Shared Access Enables Grokking, but Edit Propagation Depends on a Fine-Grained Addressable Memory

  Yanan Niu · 23 juin 2026

  We study factual edit propagation in a controlled synthetic knowledge-graph QA setting, comparing four architectures that cross loop recurrence with shared memory access: dense (Dense), looped (Loop), dense with shared memory (Dense+Mem), and looped with shared memory (LMC). Dense fits in-distributi…

• Hierarchical Pooling for Sheaf Neural Networks

  Dionisia Naddeo, Carlo Abate, Pietro Li\`o, Nicola Toschi, Filippo Maria Bianchi · 23 juin 2026

  Sheaf Neural Networks (SNNs) generalize Graph Neural Networks (GNNs) by replacing scalar node signals with stalk-valued signals and by using restriction maps to measure compatibility across edges. Unlike standard graph diffusion, which encourages neighboring node features to become similar, sheaf di…

• A Framework for Directed Acyclic Hypergraph Learning

  Zhiyuan Dong, Carlos Mundo-Levano, Wei Qian, Daniel Lau, Gonzalo R. Arce · 23 juin 2026

  Continuous optimization methods for learning Directed Acyclic Graphs (DAGs) operate on weighted adjacency matrices and are therefore limited to pairwise causal relationships. We propose a framework for learning Directed Acyclic Hypergraphs (DAHGs) from observational data, capturing joint parental in…