REVIEW 1 cited by
Generalization bounds for graph convolutional neural networks via Rademacher complexity
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
This paper aims at studying the sample complexity of graph convolutional networks (GCNs), by providing tight upper bounds of Rademacher complexity for GCN models with a single hidden layer. Under regularity conditions, theses derived complexity bounds explicitly depend on the largest eigenvalue of graph convolution filter and the degree distribution of the graph. Again, we provide a lower bound of Rademacher complexity for GCNs to show optimality of our derived upper bounds. Taking two commonly used examples as representatives, we discuss the implications of our results in designing graph convolution filters an graph distribution.
Forward citations
Cited by 1 Pith paper
-
Conv4Rec: A 1-by-1 Convolutional AutoEncoder for User Profiling through Joint Analysis of Implicit and Explicit Feedbacks
A 1-by-1 convolutional autoencoder with six-way softmax outputs jointly predicts interaction likelihood and conditional rating, supported by generalization bounds and mixed but mostly competitive RMSE and Recall resul...
Discussion (0). Continue with ORCID to comment.