Pith. sign in

REVIEW 7 cited by

InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization

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

arxiv 1908.01000 v3 pith:EG4Q65U7 submitted 2019-07-31 cs.LG cs.AIstat.ML

classification cs.LGcs.AIstat.ML
keywords infographrepresentationsgraph-levelgraphlearningsemi-supervisedunsupervisedinformation
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper studies learning the representations of whole graphs in both unsupervised and semi-supervised scenarios. Graph-level representations are critical in a variety of real-world applications such as predicting the properties of molecules and community analysis in social networks. Traditional graph kernel based methods are simple, yet effective for obtaining fixed-length representations for graphs but they suffer from poor generalization due to hand-crafted designs. There are also some recent methods based on language models (e.g. graph2vec) but they tend to only consider certain substructures (e.g. subtrees) as graph representatives. Inspired by recent progress of unsupervised representation learning, in this paper we proposed a novel method called InfoGraph for learning graph-level representations. We maximize the mutual information between the graph-level representation and the representations of substructures of different scales (e.g., nodes, edges, triangles). By doing so, the graph-level representations encode aspects of the data that are shared across different scales of substructures. Furthermore, we further propose InfoGraph*, an extension of InfoGraph for semi-supervised scenarios. InfoGraph* maximizes the mutual information between unsupervised graph representations learned by InfoGraph and the representations learned by existing supervised methods. As a result, the supervised encoder learns from unlabeled data while preserving the latent semantic space favored by the current supervised task. Experimental results on the tasks of graph classification and molecular property prediction show that InfoGraph is superior to state-of-the-art baselines and InfoGraph* can achieve performance competitive with state-of-the-art semi-supervised models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. Frequency-Corrupt Based Graph Self-Supervised Learning

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    FC-GSSL is a graph self-supervised method that corrupts nodes/edges with high low-frequency contribution and reconstructs low-frequency/general targets, improving node and graph prediction on most tested benchmarks.

  2. Graph Positional Autoencoders as Self-supervised Learners

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A dual-path graph autoencoder that reconstructs node features and Laplacian-eigenvector distances reports strong self-supervised results on heterophilic and molecular benchmarks, with some overstatement in the margins...

  3. Learnable Kernel Density Estimation for Graphs and Its Application to Graph-Level Anomaly Detection

    cs.LG 2025-05 reject novelty 6.0 of 10

    LGKDE learns a maximum mean discrepancy based graph metric and fits a multi-scale kernel density estimator, using perturbed graphs as contrastive targets for graph-level anomaly detection.

  4. Khan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negatives

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Khan-GCL combines KAN encoders with coefficient-based critical feature identification to generate hard negatives and reports state-of-the-art graph classification results.

  5. DICE: Device-level Integrated Circuits Encoder with Graph Contrastive Pretraining

    cs.LG 2025-02 conditional novelty 6.0 of 10

    A self-supervised graph encoder for device-level circuits improves prediction of circuit similarity, delays, and op-amp performance across analog and digital designs.

  6. Closer through commonality: Enhancing hypergraph contrastive learning with shared groups

    cs.LG 2025-02 conditional novelty 6.0 of 10

    HyFi improves hypergraph contrastive learning by weighting nodes that share hyperedges as 'weak positives' and using feature noise instead of topology corruption for augmentation.

  7. Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiation

    cs.SI 2025-07 conditional novelty 5.0 of 10

    CMV-ND builds one feature view per exact hop distance and then runs existing clustering methods on those views, improving attribute-missing large-scale graph clustering in experiments.

Pith tools