Pith. sign in

REVIEW 2 cited by

$f$-MICL: Understanding and Generalizing InfoNCE-based Contrastive Learning

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 2402.10150 v1 pith:APSPQQHN submitted 2024-02-15 cs.LG

classification cs.LG
keywords miclsimilaritycontrastiveinformationlearningmutualobjectivebetter
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

In self-supervised contrastive learning, a widely-adopted objective function is InfoNCE, which uses the heuristic cosine similarity for the representation comparison, and is closely related to maximizing the Kullback-Leibler (KL)-based mutual information. In this paper, we aim at answering two intriguing questions: (1) Can we go beyond the KL-based objective? (2) Besides the popular cosine similarity, can we design a better similarity function? We provide answers to both questions by generalizing the KL-based mutual information to the $f$-Mutual Information in Contrastive Learning ($f$-MICL) using the $f$-divergences. To answer the first question, we provide a wide range of $f$-MICL objectives which share the nice properties of InfoNCE (e.g., alignment and uniformity), and meanwhile result in similar or even superior performance. For the second question, assuming that the joint feature distribution is proportional to the Gaussian kernel, we derive an $f$-Gaussian similarity with better interpretability and empirical performance. Finally, we identify close relationships between the $f$-MICL objective and several popular InfoNCE-based objectives. Using benchmark tasks from both vision and natural language, we empirically evaluate $f$-MICL with different $f$-divergences on various architectures (SimCLR, MoCo, and MoCo v3) and datasets. We observe that $f$-MICL generally outperforms the benchmarks and the best-performing $f$-divergence is task and dataset dependent.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Representation Learning via Non-Contrastive Mutual Information

    cs.LG 2025-04 conditional novelty 6.0 of 10

    The MINC loss converts the Spectral Contrastive loss into a non-contrastive form via power iteration and a Hebbian orthogonality update, preventing collapse and improving ImageNet representation accuracy over the cont...

  2. Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A contrastive self-supervised loss is shown to be equivalent to learning the evolution operator's spectral decomposition, recovering slow modes in proteins, ligand binding, and ENSO climate data.

Pith tools