LLMs achieve strong results on text-attributed graphs using only node textual descriptions, while most methods for encoding graph structure deliver marginal or negative gains.
Title resolution pending
3 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
3
Pith papers citing it
1
external citations · external index
representative citing papers
DNSD replaces the sheaf Laplacian with a sheaf adjacency operator, adds normalization and gating, and empirically outperforms GNN and NSD baselines by up to 30 percentage points on synthetic long-range graph tasks while also improving on real-world benchmarks.
A review paper that surveys AI uses across the food innovation pipeline for sustainable proteins and identifies four strategic priorities for the emerging field.
citing papers explorer
-
When Structure Doesn't Help: LLMs Do Not Read Text-Attributed Graphs as Effectively as We Expected
LLMs achieve strong results on text-attributed graphs using only node textual descriptions, while most methods for encoding graph structure deliver marginal or negative gains.
-
Deep Neural Sheaf Diffusion
DNSD replaces the sheaf Laplacian with a sheaf adjacency operator, adds normalization and gating, and empirically outperforms GNN and NSD baselines by up to 30 percentage points on synthetic long-range graph tasks while also improving on real-world benchmarks.
-
Artificial Intelligence for Food Innovation
A review paper that surveys AI uses across the food innovation pipeline for sustainable proteins and identifies four strategic priorities for the emerging field.