- Forming Scalable, Convergent GNN Layers that Minimize a Sampling-Based Energy
- Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barrier
- ST-GCond: Self-supervised and Transferable Graph Dataset Condensation
- Graph Sparsification via Mixture of Graphs
- Accurate and Scalable Graph Neural Networks via Message Invariance
- Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning
- Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs
- Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs
- Understanding Virtual Nodes: Oversquashing and Node Heterogeneity
- Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing
- Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks
- GLoRa: A Benchmark to Evaluate the Ability to Learn Long-Range Dependencies in Graphs
- Joint Graph Rewiring and Feature Denoising via Spectral Resonance
- Spectral Graph Coarsening Using Inner Product Preservation and the Grassmann Manifold
- GRASP: Generating Graphs via Spectral Diffusion
- When Graph Neural Networks Meet Dynamic Mode Decomposition
- Revisiting Random Walks for Learning on Graphs
- Learning Long Range Dependencies on Graphs via Random Walks
- Graph Transformers Dream of Electric Flow
- Unleashing Graph Transformers with Green and Martin Kernels
- Training-Free Message Passing for Learning on Hypergraphs
- Link Prediction with Relational Hypergraphs
- TopoTune: A Framework for Generalized Combinatorial Complex Neural Networks
- Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity
- E(n) Equivariant Topological Neural Networks
- Is uniform expressivity too restrictive? Towards efficient expressivity of GNNs
- Rethinking the Expressiveness of GNNs: A Computational Model Perspective
- Diss-l-ECT: Dissecting Graph Data with local Euler Characteristic Transforms
- On the Hölder Stability of Multiset and Graph Neural Networks
- Towards Stable, Globally Expressive Graph Representations with Laplacian Eigenvectors
- Towards a Complete Logical Framework for GNN Expressiveness
- Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs
- Graph Neural Networks Can (Often) Count Substructures
- Homomorphism Counts as Structural Encodings for Graph Learning
- Homomorphism Expressivity of Spectral Invariant Graph Neural Networks
- Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs
- Towards Bridging Generalization and Expressivity of Graph Neural Networks
- Instant Policy: In-Context Imitation Learning via Graph Diffusion
- Bundle Neural Network for message diffusion on graphs
- Relation-Aware Diffusion for Heterogeneous Graphs with Partially Observed Features
- AdaRC: Mitigating Graph Structure Shifts during Test-Time
- Diversifying Spurious Subgraphs for Graph Out-of-Distribution Generalization
- Towards Generalization Bounds of GCNs for Adversarially Robust Node Classification
- Robustness Inspired Graph Backdoor Defense
- Learning Randomized Algorithms with Transformers
- Certified Defense on the Fairness of Graph Neural Networks
- Exact Certification of (Graph) Neural Networks Against Label Poisoning
- Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoors
- GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation
- STOP! A Out-of-Distribution Processor with Robust Spatiotemporal Interaction
- Spreading Out-of-Distribution Detection on Graphs
- Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark
- SpaceGNN: Multi-Space Graph Neural Network for Node Anomaly Detection with Extremely Limited Labels
- N-ForGOT: Towards Not-forgetting and Generalization of Open Temporal Graph Learning
- Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting
- TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics
- MEMFREEZING: TOWARDS PRACTICAL ADVERSARIAL ATTACKS ON TEMPORAL GRAPH NEURAL NETWORKS
- Rationalizing and Augmenting Dynamic Graph Neural Networks
- Explanations of GNN on Evolving Graphs via Axiomatic Layer edges
- GraphBridge: Towards Arbitrary Transfer Learning in GNNs
- Towards Continuous Reuse of Graph Models via Holistic Memory Diversification
- Holographic Node Representations: Pre-training Task-Agnostic Node Embeddings
- Centrality-guided Pre-training for Graph
- Edge Prompt Tuning for Graph Neural Networks
- Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysis
- GOFA: A Generative One-For-All Model for Joint Graph Language Modeling
- Scale-Free Graph-Language Models
- Language Representations Can be What Recommenders Need: Findings and Potentials
- Circuit Representation Learning with Masked Gate Modeling and Verilog-AIG Alignment
- Can LLMs Enhance Performance Prediction for Deep Learning Models?
- GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning
- What Are Good Positional Encodings for Directed Graphs?
- A Benchmark on Directed Graph Representation Learning in Hardware Designs
- Graph Neural Networks for Edge Signals: Orientation Equivariance and Invariance
- LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation
- Neural Spacetimes for DAG Representation Learning
- Beyond Directed Acyclic Computation Graph with Cyclic Neural Network
- Estimation of single-cell and tissue perturbation effect in spatial transcriptomics via Spatial Causal Disentanglement
- GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation
- DHENN: A Deeper Hybrid End-to-end Neural Network for Highly Accurate Drug-Drug Interaction Events Prediction
- CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph
- Global Context-aware Representation Learning for Spatially Resolved Transcriptomics
- A Theoretically-Principled Sparse, Connected, and Rigid Graph Representation of Molecules
- Force-Guided Bridge Matching for Full-Atom Time-Coarsened Dynamics of Peptides
- REBIND: Enhancing Ground-state Molecular Conformation Prediction via Force-Based Graph Rewiring
- Learning Molecular Representation in a Cell
- Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning
- Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space
- E(3)-equivariant models cannot learn chirality: Field-based molecular generation
- Geometry Informed Tokenization of Molecules for Language Model Generation
- Learning Equivariant Non-Local Electron Density Functionals
- Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects
- Improving Equivariant Networks with Probabilistic Symmetry Breaking
- VN-EGNN: E(3)- and SE(3)-Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification
- Periodic Materials Generation using Text-Guided Joint Diffusion Model
- Invariant Graphon Networks: Approximation and Cut Distance
- Rethinking the role of frames for SE(3)-invariant crystal structure modeling
- PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systems
- Spatiotemporal Learning on Cell-embedded Graphs
- Learning Distributions of Complex Fluid Simulations with Diffusion Graph Networks
- SPARK: Physics-Guided Quantitative Augmentation for Dynamical System Modeling
- Data Center Cooling System Optimization Using Offline Reinforcement Learning
- Learning Splitting Heuristics in Divide-and-Conquer SAT Solvers with Reinforcement Learning
- Training One-Dimensional Graph Neural Networks is NP-Hard
- Accelerating Training with Neuron Interaction and Nowcasting Networks
- BiQAP: Neural Bi-level Optimization-based Framework for Solving Quadratic Assignment Problems
- Learning to Select Nodes in Branch and Bound with Sufficient Tree Representation
- BTBS-LNS: Binarized-Tightening, Branch and Search on Learning LNS Policies for MIP
- GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networks
- A Generic Framework for Conformal Fairness
- HGM³: Hierarchical Generative Masked Motion Modeling with Hard Token Mining
- BaB-ND: Long-Horizon Motion Planning with Branch-and-Bound and Neural Dynamics
- Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians
- A Graph Enhanced Symbolic Discovery Framework For Efficient Circuit Synthesis
- A Large-scale Dataset and Benchmark for Commuting Origin-Destination Flow Generation
- GlycanML: A Multi-Task and Multi-Structure Benchmark for Glycan Machine Learning
- Implicit degree bias in the link prediction task
- When do GFlowNets learn the right distribution?
- Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning
- Multi-Label Node Classification with Label Influence Propagation
- DAS-GNN: Degree-Aware Spiking Graph Neural Networks for Graph Classification
- Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs
- BANGS: Game-theoretic Node Selection for Graph Self-Training
- Collective variables of neural networks: empirical time evolution and scaling laws
- Graph Neural Networks Gone Hogwild
- PolyhedronNet: Representation Learning for Polyhedra with Surface-attributed Graph
- Clique Number Estimation via Differentiable Functions of Adjacency Matrix Permutations