SpecValley: Aggregation as Spectral Valley in Dense Heterophilic Graphs
cs.CV, cs.LG
Submitted: 2026-11-10
Updated: 2026-11-10
Terminology
Sources
- Graph Attention Networks
- MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
- Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
- Deep Graph Infomax
- Contrastive Multi-View Representation Learning on Graphs
- GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
- Learning Discrete Structures for Graph Neural Networks
- Equivariant Machine Learning on Graphs with Nonlinear Spectral Filters
- Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
- Beyond Low-frequency Information in Graph Convolutional Networks
- BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
- How Powerful are Spectral Graph Neural Networks
- Recipe for a General, Powerful, Scalable Graph Transformer
- Rethinking Graph Transformers with Spectral Attention
- Label-Wise Graph Convolutional Network for Heterophilic Graphs
- Inductive Representation Learning on Large Graphs
- Gophormer: Ego-Graph Transformer for Node Classification
- Spectral Networks and Locally Connected Networks on Graphs
- Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
- GraphLand: Evaluating Graph Machine Learning Models on Diverse Industrial Data
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs