Awesome Theory & Expressivity

Key papers

• Improved large-scale graph learning through ridge spectral sparsification (2026)
  Daniele Calandriello et al.
  9.39
• Graph Kernel Neural Networks (2021)
  Luca Cosmo et al.
  7.59
• Explaining GNN Explanations with Edge Gradients (2025)
  Jesse He et al.
  5.57
• When Design Rules Break: Benchmark Composition Determines Whether Label Informativeness Predicts GNN Aggregator Choice (2026)
  Neha Sharma et al.
  5.49
• Mitigating Degree Bias in Graph Representation Learning with Learnable Structural Augmentation and Structural Self-Attention (2025)
  Van Thuy Hoang et al.
  5.35
• Recent Advances in Hypergraph Neural Networks (2025)
  Murong Yang et al.
  5.29
• Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic Decomposition (2025)
  Heesoo Jung et al.
  4.93
• Uncertainty-Aware Graph Structure Learning (2025)
  Shen Han et al.
  4.82
• X-Node: Self-Explanation is All We Need (2025)
  Prajit Sengupta and Islem Rekik
  4.78
• Bayesian Membership Privacy for Graph Neural Networks (2026)
  Sinan Y{\i}ld{\i}r{\i}m et al.
  4.39
• Graph Cascades: Contagion-Based Mesoscopic Rewiring for Structure-Aware Graph Machine Learning (2026)
  Meher Chaitanya et al.
  4.39
• Graph Set Transformer (2026)
  Jose E. Escrig Molina et al.
  4.39
• Graph Neural Network leveraging Higher-order Class Label Connectivity for Heterophilous Graphs (2026)
  Takuto Takahashi et al.
  4.39
• Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passing (2026)
  Lianze Shan et al.
  4.39
• ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed Graphs (2026)
  Xianlin Zeng et al.
  4.39
• LLMs+Graphs: Toward Graph-Native, Synergistic AI Systems (2026)
  Arijit Khan et al.
  4.39
• Artemis: Anatomy-Resolved inTervention for Eliminating Multimodal NeuroImage confounderS (2026)
  Siyuan Dai et al.
  4.39
• Enhanced Graph Neural Networks using K-Hop Gaussian Diffusion (2026)
  Xuling Zhang et al.
  4.39
• AGDN: Learning to Solve Traveling Salesman Problem with Anisotropic Graph Diffusion Network (2026)
  Bolin Shen et al.
  4.39
• P-K-GCN: Physics-augmented Koopman-enhanced Graph Convolutional Network for Deep Spatiotemporal Super-resolution (2026)
  Xizhuo (Cici) et al.
  4.39
• Projecting Latent RL Actions: Towards Generalizable and Scalable Graph Combinatorial Optimization (2026)
  Franco Terranova (UL et al.
  4.33
• Graph Navier Stokes Networks (2026)
  Zexing Zhao et al.
  4.33
• Gaussian Sheaf Neural Networks (2026)
  Andr\'e Ribeiro et al.
  4.33
• EvoStruct: Bridging Evolutionary and Structural Priors for Antibody CDR Design via Protein Language Model Adaptation (2026)
  Mansoor Ahmed et al.
  4.33
• Expressive Power of Deep Homomorphism Networks over Relational Databases (2026)
  Moritz Sch\"onherr et al.
  4.33
• Graph Alignment Topology as an Inductive Bias for Grounding Detection (2026)
  Paul Landes et al.
  4.33
• Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them (2026)
  Snir Hordan et al.
  4.33
• Relevant Walk Search for Explaining Graph Neural Networks (2026)
  Ping Xiong et al.
  4.33
• Fuzzy, Neutrosophic, and Uncertain Graph Theory: Properties and Applications (2026)
  Takaaki Fujita et al.
  4.33
• Beyond the Aggregation Dilemma: Prior-Retaining Decoupled Learning for Multimodal Graphs (2026)
  Hao Yan et al.
  4.33
• Aligning Molecular Graph Explanations with Chemical Identity via InChIfied Invariants (2026)
  Emanuele Guidotti et al.
  4.33
• Clustering as Reasoning: A $k$-Means Interpretation of Chain-of-Thought Graph Learning (2026)
  Xuanting Xie et al.
  4.33
• Revisiting Pre-Propagation GNNs: Robust Diffusion Operators and Hidden-State Re-Propagation (2026)
  Zichao Yue et al.
  4.33
• Closed-Form Node Classification with Exact Graph Unlearning (2026)
  Aditya Gaur et al.
  4.33
• What Molecular Structure Cannot Tell Us: A Taxonomy of Explainability Gaps in GNN-Based Drug Toxicity Prediction (2026)
  Juergen Dietrich
  4.33
• Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks (2026)
  Zhishuai Guo et al.
  4.33
• RAPNet: Accelerating Algebraic Multigrid with Learned Sparse Corrections (2026)
  Yali Fink et al.
  4.33
• T-GINEE: A Tensor-Based Multilayer Graph Representation Learning (2026)
  Maolin Wang et al.
  4.33
• A Generalized Tikhonov Layer for Interpretable-by-design Graph Neural Networks (2026)
  Nicolas Tremblay et al.
  4.33
• AbstainGNN: Teaching Graph Neural Networks to Abstain for Graph Classification (2026)
  Xixun Lin et al.
  4.33
• An Efficient and Scalable Graph Condensation with Structure-Preserving (2026)
  Yulin Hu et al.
  4.33
• Graph Neural Networks Are Not Continuous Across Graph Resolutions (2026)
  Christian Koke et al.
  4.33
• Scaling Higher-Order Graph Learning with Maximal Clique Complexes (2026)
  Antoine Vialle et al.
  4.33
• Can Classic GNNs Be Strong Baselines for Graph-level Tasks? Simple Architectures Meet Excellence (2025)
  Yuankai Luo et al.
  4.30
• Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs (2025)
  Batu El et al.
  4.30
• The Underappreciated Power of Vision Models for Graph Structural Understanding (2025)
  Xinjian Zhao et al.
  4.09
• Graph Neural Network Prediction of Nonlinear Optical Properties (2025)
  Yomn Alkabakibi et al.
  3.75
• Graph Neural Network-Driven Hierarchical Mining for Complex Imbalanced Data (2025)
  Yijiashun Qi et al.
  3.64
• To Bin or not to Bin: Alternative Representations of Mass Spectra (2025)
  Niek de Jonge et al.
  3.64
• Efficient Transition State Searches by Freezing String Method with Graph Neural Network Potentials (2025)
  Jonah Marks and Joseph Gomes
  3.59
• Learning Non-Local Molecular Interactions via Equivariant Local Representations and Charge Equilibration (2025)
  Paul Fuchs et al.
  3.59
• Different Statistical Perspectives for Understanding Generalisation in Graph Neural Networks (2026)
  Nil Ayday et al.
  3.45
• Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks? (2026)
  Ojas Nimase et al.
  3.45
• VS-Graph: Scalable and Efficient Graph Classification Using Hyperdimensional Computing (2025)
  Hamed Poursiami et al.
  3.26
• CycleChemist: A Dual-Pronged Machine Learning Framework for Organic Photovoltaic Discovery (2025)
  Hou Hei Lam et al.
  3.21
• Multimodal Regression for Enzyme Turnover Rates Prediction (2025)
  Bozhen Hu et al.
  3.10
• A Graph-Neural-Network-Entropy model of vital node identification on network attack and propagation (2025)
  Huaizhi Liao et al.
  3.10
• GNN-based Unified Deep Learning (2025)
  Furkan Pala and Islem Rekik
  3.04
• Understanding and Tackling Over-Dilution in Graph Neural Networks (2025)
  Junhyun Lee et al.
  3.04
• Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax (2025)
  Marcel Hoffmann and Lukas Galke and Ansgar Scherp
  3.04