ONDA: Operator-Valued Information Waves Fix Long-Range Propagation in GNNs
burny_tech · x · 2026-10-27
The paper introduces ONDA, a long-range graph learning framework built on operator-valued information waves. Stalk-valued representations evolve under second-order dynamics governed by learned sheaf transport operators, combining wave-like propagation with expressive local geometry. Sensitivity analysis shows cross-node influence never vanishes, and ONDA consistently beats scalar wave propagation, diffusive sheaf baselines, and SOTA models on long-range, bottleneck, graph-transfer, and heterophilic benchmarks.
Related event: ONDA: Oscillatory Neural Dynamics Tackle Long-Range Propagation in GNNs(2 posts)→
More from Research
- Scientists argue research scaling is 80% one-pot protocols, not lab automation — clarejtbirch · 2026-10-27
- Yoav Artzi simulates 4 capped-reviewing mechanisms on real COLM data: 12-24% of accepted papers left out — yoavartzi · 2026-10-27
- Experiment finds 9 'gender neurons' in Qwen3.5-4B that flip its self-identity — burny_tech · 2026-10-27
- GPT-6-Astra embodied intelligence eval: near-100% on several of 12 benchmarks — chris_j_paxton · 2026-10-27
- LEANN open-source RAG project claims 97% vector DB storage savings: 201GB to 6GB — Promptmethus · 2026-10-27
- Claude Opus 5.5 claims ETH false, all-dimension Kakeya and Yang-Mills in one day — repligate · 2026-10-27