REVIEW 3 cited by
MotifNet: a motif-based Graph Convolutional Network for directed graphs
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Deep learning on graphs and in particular, graph convolutional neural networks, have recently attracted significant attention in the machine learning community. Many of such techniques explore the analogy between the graph Laplacian eigenvectors and the classical Fourier basis, allowing to formulate the convolution as a multiplication in the spectral domain. One of the key drawback of spectral CNNs is their explicit assumption of an undirected graph, leading to a symmetric Laplacian matrix with orthogonal eigendecomposition. In this work we propose MotifNet, a graph CNN capable of dealing with directed graphs by exploiting local graph motifs. We present experimental evidence showing the advantage of our approach on real data.
Forward citations
Cited by 3 Pith papers
-
Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation
GaRA generates task-specific LoRA weight updates conditioned on graph structures to enable better whole-graph encoding in LLMs for zero-shot graph learning.
-
AI Generalisation Gap In Comorbid Sleep Disorder Staging
EEG sleep-staging models that work on healthy subjects generalize poorly to ischemic stroke patients and attend to physiologically uninformative signal regions.
-
Motif-Mamba: network motif improved mamba for long-range sequence modeling
A low-rank, motif-constrained recurrent coupling improves Mamba's language modeling and long-sequence recall by a few tenths of a point.
Discussion (0). Sign in to comment.