NearFormer: Linear-Size Sparse Attention via Randomized Near Neighbors
cs.LG, cs.AI
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- On the Bottleneck of Graph Neural Networks and its Practical Implications
- DiffWire: Inductive Graph Rewiring via the Lov'asz Bound
- Comparing Graph Transformers via Positional Encodings
- Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
- Residual Gated Graph ConvNets
- NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs
- Higher-Order Expander Graph Propagation
- Graph Neural Networks with Learnable Structural and Positional Representations
- Long Range Graph Benchmark
- GraphiT: Encoding Graph Structure in Transformers
- Recipe for a General, Powerful, Scalable Graph Transformer
- A Survey on Oversmoothing in Graph Neural Networks
- Exposition on over-squashing problem on GNNs: Current Methods, Benchmarks and Challenges
- Efficient Transformers: A Survey
- DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion
- Do Transformers Really Perform Bad for Graph Representation?
- Graph-Bert: Only Attention is Needed for Learning Graph Representations
- Gophormer: Ego-Graph Transformer for Node Classification
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis