Pith. sign in

REVIEW 3 cited by

A Generalization of Convolutional Neural Networks to Graph-Structured Data

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 1704.08165 v1 pith:WC6JPZRR submitted 2017-04-26 stat.ML cs.AIcs.CVcs.LG

Yotam Hechtlinger , Purvasha Chakravarti , Jining Qin This is my paper · ORCID
classification stat.MLcs.AIcs.CVcs.LG
keywords dataconvolutiongeneralizationconvolutionalgraphgraph-structuredgridnetworks
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

This paper introduces a generalization of Convolutional Neural Networks (CNNs) from low-dimensional grid data, such as images, to graph-structured data. We propose a novel spatial convolution utilizing a random walk to uncover the relations within the input, analogous to the way the standard convolution uses the spatial neighborhood of a pixel on the grid. The convolution has an intuitive interpretation, is efficient and scalable and can also be used on data with varying graph structure. Furthermore, this generalization can be applied to many standard regression or classification problems, by learning the the underlying graph. We empirically demonstrate the performance of the proposed CNN on MNIST, and challenge the state-of-the-art on Merck molecular activity data set.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Neural Algorithmic Reasoners informed Large Language Model for Multi-Agent Path Finding

    cs.AI 2025-08 unverdicted novelty 6.0 of 10

    A graph-neural-network-based algorithmic reasoner feeds map and planning information to an LLM through cross-attention, improving multi-agent path finding over LLM-only baselines.

  2. Graph Neural Networks in Wind Power Forecasting

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A message-passing GNN matches a CNN baseline for 24 to 36 hour ahead wind power forecasts across three wind farms, with small MAE differences in both directions.

  3. Robust Quantum Reservoir Computing for Molecular Property Prediction

    quant-ph 2024-12 conditional novelty 5.0 of 10

    Quantum reservoir computing embeddings give more stable molecular activity predictions than classical models on small training sets in the Merck Molecular Activity Challenge benchmark.

Pith tools