GAT Author Petar Veličković Teases Final Chapter of Graph Learning Work
PetarV_93 · x · 2026-11-09
Petar Veličković, DeepMind researcher and GAT co-author, posted "the final chapter is in sight" with several paper figures showing message-passing time-unrolling structures, multiscale/wavelet-style graph operators (W(0,v), F(H)(t,u)), and permutation/automorphism symmetry analysis on graphs.
The figures suggest the concluding installment of his graph learning theory series; details await the full paper.
More from Research
- Survey by 30+ authors maps modern NLP tokenization, from subword wins to its flaws — rdesh26 · 2026-11-09
- No 8 GPUs needed: six hands-on steps to actually understand transformers — cneuralnetwork · 2026-11-09
- SwarmEvolve: 450 latent-space agents boost program search 5-13x — aigclink · 2026-11-09
- ByteDance Seed's Hierarchical Residuals decouple residual width from compute width in Transformers — ByteDance-Seed · 2026-11-09
- Paper in Phil Trans B: human-AI agent interactions are bidirectional and reshape who we are — AnnaCiaunica · 2026-11-09
- Even top 3D-gen models keep making the same basic mistakes, researcher notes — teortaxesTex · 2026-11-09