GNNs are shown to lack continuity under graph resolution changes due to message-passing schemes, with a derived modification enabling consistent multi-scale representations validated experimentally.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
IO-aware GPU kernels for SpMM convolutions, degree-aware reductions, and fused attention layers deliver median speedups of 1.6-2.6x (up to 10x) and memory reductions up to 76x over DGL/PyG baselines on realistic graphs.
RankGraph-2 jointly optimizes graph construction, training, and serving for billion-node recommendation retrieval, reporting 3.8x recall gains and CTR/CVR improvements via subsampling, pre-computed neighborhoods, and co-learned indexing.
citing papers explorer
-
Graph Neural Networks Are Not Continuous Across Graph Resolutions
GNNs are shown to lack continuity under graph resolution changes due to message-passing schemes, with a derived modification enabling consistent multi-scale representations validated experimentally.
-
On Efficient Scaling of GNNs via IO-Aware Layers Implementations
IO-aware GPU kernels for SpMM convolutions, degree-aware reductions, and fused attention layers deliver median speedups of 1.6-2.6x (up to 10x) and memory reductions up to 76x over DGL/PyG baselines on realistic graphs.