- Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness
- Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching
- Graph Distillation with Eigenbasis Matching
- GNNs Also Deserve Editing, and They Need It More Than Once
- Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs
- Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning
- Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective
- SLOG: An Inductive Spectral Graph Neural Network Beyond Polynomial Filter
- Mitigating Oversmoothing Through Reverse Process of GNNs for Heterophilic Graphs
- Understanding Heterophily for Graph Neural Networks
- Optimal Exact Recovery in Semi-Supervised Learning: A Study of Spectral Methods and Graph Convolutional Networks
- On Which Nodes Does GCN Fail? Enhancing GCN From the Node Perspective
- Mitigating Label Noise on Graphs via Topological Sample Selection
- GATE: How to Keep Out Intrusive Neighbors
- Graph External Attention Enhanced Transformer
- DUPLEX: Dual GAT for Complex Embedding of Directed Graphs
- Less is More: on the Over-Globalizing Problem in Graph Transformers
- How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing
- Multi-Track Message Passing: Tackling Oversmoothing and Oversquashing in Graph Learning via Preventing Heterophily Mixing
- Delaunay Graph: Addressing Over-Squashing and Over-Smoothing Using Delaunay Triangulation
- PANDA: Expanded Width-Aware Message Passing Beyond Rewiring
- Subhomogeneous Deep Equilibrium Models
- Recurrent Distance Filtering for Graph Representation Learning
- Privacy Attacks in Decentralized Learning
- Graph Adversarial Diffusion Convolution
- Collective Certified Robustness against Graph Injection Attacks
- Verifying message-passing neural networks via topology-based bounds tightening
- Rethinking Independent Cross-Entropy Loss For Graph-Structured Data
- Tackling Non-Stationarity in Reinforcement Learning via Causal-Origin Representation
- From Geometry to Causality- Ricci Curvature and the Reliability of Causal Inference on Networks
- Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks
- Explaining Graph Neural Networks via Structure-aware Interaction Index
- How Interpretable Are Interpretable Graph Neural Networks?
- Prospector Heads: Generalized Feature Attribution for Large Models & Data
- Graph Neural Network Explanations are Fragile
- EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time
- On the Expressive Power of Spectral Invariant Graph Neural Networks
- Homomorphism Counts for Graph Neural Networks: All About That Basis
- The Expressive Power of Path-Based Graph Neural Networks
- An Empirical Study of Realized GNN Expressiveness
- Weisfeiler-Leman at the margin: When more expressivity matters
- Cooperative Graph Neural Networks
- Graph As Point Set
- Aligning Transformers with Weisfeiler-Leman
- On dimensionality of feature vectors in MPNNs
- Weisfeiler Leman for Euclidean Equivariant Machine Learning
- Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products
- Editing Partially Observable Networks via Graph Diffusion Models
- Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning
- Equivariant Graph Neural Operator for Modeling 3D Dynamics
- Graph Neural PDE Solvers with Conservation and Similarity-Equivariance
- Improving Equivariant Graph Neural Networks on Large Geometric Graphs via Virtual Nodes Learning
- Graph Automorphism Group Equivariant Neural Networks
- Interpreting Equivariant Representations
- Topological Neural Networks go Persistent, Equivariant, and Continuous
- Exploiting Code Symmetries for Learning Program Semantics
- EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction
- HGAP: Boosting Permutation Invariant and Permutation Equivariant in Multi-Agent Reinforcement Learning via Graph Attention Network
- SiT: Symmetry-invariant Transformers for Generalisation in Reinforcement Learning
- On the Generalization of Equivariant Graph Neural Networks
- What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding
- Disentangled Graph Self-supervised Learning for Out-of-Distribution Generalization
- How Graph Neural Networks Learn: Lessons from Training Dynamics
- Graph Neural Networks Use Graphs When They Shouldn�t
- Neural Tangent Kernels Motivate Cross-Covariance Graphs in Neural Networks
- Generalization Error of Graph Neural Networks in the Mean-field Regime
- Enhancing Size Generalization in Graph Neural Networks through Disentangled Representation Learning
- EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphs
- CARTE: Pretraining and Transfer for Tabular Learning
- Pairwise Alignment Improves Graph Domain Adaptation
- Graph Structure Extrapolation for Out-of-Distribution Generalization
- Graph Out-of-Distribution Detection Goes Neighborhood Shaping
- Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs
- Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design
- Prometheus: Out-of-distribution Fluid Dynamics Modeling with Disentangled Graph ODE
- Empowering Graph Invariance Learning with Deep Spurious Infomax
- LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering
- Modelling Microbial Communities with Graph Neural Networks
- On the Role of Edge Dependency in Graph Generative Models
- Hyperbolic Geometric Latent Diffusion Model for Graph Generation
- Diffuse, Sample, Project: Plug-And-Play Controllable Graph Generation
- Graph Generation with Diffusion Mixture
- Scene Graph Generation Strategy with Co-occurrence Knowledge and Learnable Term Frequency
- PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning
- Knowledge Graphs Can be Learned with Just Intersection Features
- KnowFormer: Revisiting Transformers for Knowledge Graph Reasoning
- Embodied CoT Distillation From LLM To Off-the-shelf Agents
- GPTSwarm: Language Agents as Optimizable Graphs
- CHEMREASONER: Heuristic Search over a Large Language Model�s Knowledge Space using Quantum-Chemical Feedback
- MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models
- LLaGA: Large Language and Graph Assistant
- LaMAGIC: Language-Model-based Topology Generation for Analog Integrated Circuits
- Graph-enhanced Large Language Models in Asynchronous Plan Reasoning
- Knowledge-aware Reinforced Language Models for Protein Directed Evolution
- Proteus: Exploring Protein Structure Generation for Enhanced Designability and Efficiency
- Hypergraph-enhanced Dual Semi-supervised Graph Classification
- Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective
- Structure Your Data: Towards Semantic Graph Counterfactuals
- MS-TIP: Imputation Aware Pedestrian Trajectory Prediction
- VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context
- Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition
- Effective Federated Graph Matching
- Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients
- Federated Self-Explaining GNNs with Anti-shortcut Augmentations
- Class-Imbalanced Graph Learning without Class Rebalancing
- Automated Loss function Search for Class-imbalanced Node Classification
- Towards Neural Architecture Search through Hierarchical Generative Modeling
- Disentangled Continual Graph Neural Architecture Search with Invariant Modular Supernet
- Surprisingly Strong Performance Prediction with Neural Graph Features
- Encodings for Prediction-based Neural Architecture Search
- Graph Neural Stochastic Diffusion for Estimating Uncertainty in Node Classification
- Uncertainty for Active Learning on Graphs
- HGCN2SP: Hierarchical Graph Convolutional Network for Two-Stage Stochastic Programming
- Graph Neural Networks with a Distribution of Parametrized Graphs
- Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning
- Long Range Propagation on Continuous-Time Dynamic Graphs
- Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling
- Graph-based Time Series Clustering for End-to-End Hierarchical Forecasting
- UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis
- Irregular Multivariate Time Series Forecasting: A Transformable Patching Graph Neural Networks Approach
- Comparing Graph Transformers via Positional Encodings
- Graph Positional and Structural Encoder
- CKGConv: General Graph Convolution with Continuous Kernels
- Quantum Positional Encodings for Graph Neural Networks
- QBMK: Quantum-based Matching Kernels for Un-attributed Graphs
- From Coarse to Fine: Enable Comprehensive Graph Self-supervised Learning with Multi-granular Semantic Ensemble
- Exploring Correlations of Self-Supervised Tasks for Graphs
- Efficient Contrastive Learning for Fast and Accurate Inference on Graphs
- Perfect Alignment May be Poisonous to Graph Contrastive Learning
- Community-Invariant Graph Contrastive Learning
- S3GCL: Spectral, Swift, Spatial Graph Contrastive Learning
- UniCorn: A Unified Contrastive Learning Approach for Multi-view Molecular Representation Learning
- Projecting Molecules into Synthesizable Chemical Spaces
- Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers
- Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks
- Expressivity and Generalization: Fragment-Biases for Molecular GNNs
- A Graph is Worth $K$ Words: Euclideanizing Graph using Pure Transformer
- Generalist Equivariant Transformer Towards 3D Molecular Interaction Learning
- Swallowing the Bitter Pill: Simplified Scalable Conformer Generation
- Unsupervised Representation Learning of Brain Activity via Bridging Voxel Activity and Functional Connectivity
- Neurodegenerative Brain Network Classification via Adaptive Diffusion with Temporal Regularization
- REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Updates
- OxyGenerator: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning
- DiffDA: a Diffusion model for weather-scale Data Assimilation
- Pluvial Flood Emulation with Hydraulics-informed Message Passing
- The Merit of River Network Topology for Neural Flood Forecasting
- Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments
- Finite Volume Features, Global Geometry Representations, and Residual Training for Deep Learning-based CFD Simulation
- Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics
- Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks
- Neural SPH: Improved Neural Modeling of Lagrangian Fluid Dynamics
- HAMLET: Graph Transformer Neural Operator for Partial Differential Equations
- PGODE: Towards High-quality System Dynamics Modeling
- Open Ad Hoc Teamwork with Cooperative Game Theory
- Learning Latent Structures in Network Games via Data-Dependent Gated-Prior Graph Variational Autoencoders
- Tackling Prevalent Conditions in Unsupervised Combinatorial Optimization: Cardinality, Minimum, Covering, and More
- Towards General Algorithm Discovery for Combinatorial Optimization: Learning Symbolic Branching Policy from Bipartite Graph
- Extending Test-Time Augmentation with Metamorphic Relations for Combinatorial Problems
- Predicting Lagrangian Multipliers for Mixed Integer Linear Programs
- PDHG-Unrolled Learning-to-Optimize Method for Large-Scale Linear Programming
- Position: Future Directions in the Theory of Graph Machine Learning
- Position: Graph Foundation Models Are Already Here
- Position: Relational Deep Learning - Graph Representation Learning on Relational Databases
- Position: Topological Deep Learning is the New Frontier for Relational Learning
- Simulation of Graph Algorithms with Looped Transformers
- Unsupervised Episode Generation for Graph Meta-learning
- Graph Mixup on Approximate Gromov-Wasserstein Geodesics
- CurBench: Curriculum Learning Benchmark
- Differentiability and Optimization of Multiparameter Persistent Homology
- Learning Graph Representation via Graph Entropy Maximization
- Graph Geometry-Preserving Autoencoders
- MAGNOLIA: Matching Algorithms via GNNs for Online Value-to-go Approximation
- Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Prediction
- Graph2Tac: Online Representation Learning of Formal Math Concepts
- Unsupervised Parameter-free Simplicial Representation Learning with Scattering Transforms