Research map / Architectures and efficiency / Attention and transformers
Poly-attention: a general scheme for higher-order self-attention
Sayak Chakrabarti, Toniann Pitassi, Josh Alman
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace one-layer self-attention with one-layer tree-attention | single-head Transformer · function composition f1(f2(x)) | learnability | Improved |
| use tree-attention instead of two-layer self-attention | single-head Transformer · function composition f1(f2(x)) | training epochs to learn | Improved |
| use tree-attention instead of self-attention | simple networks · COGS | accuracy | Improved |
| use tree-attention instead of self-attention | single-layer attention · inference time | relative inference time: around 1.3x time as that of self-attention | Hurt |
Closest papers by meaning
- Attention Mechanism, Max-Affine Partition, and Universal Approximation (NeurIPS 2025 · similarity 0.89)
- PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels (ICML 2024 · similarity 0.88)
- Mixture-of-Top-$k$ Attention: Efficient Attention as Scalable Fast Weights (NeurIPS 2026 · similarity 0.88)
- Fast attention mechanisms: a tale of parallelism (NeurIPS 2025 · similarity 0.87)
- Learning Linear Attention in Polynomial Time (NeurIPS 2025 · similarity 0.87)
- A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization (ICML 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
