Pith. sign in

REVIEW

ACCon: Angle-Compensated Contrastive Regularizer for Deep Regression

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 2501.07045 v1 pith:ERCAJEMY submitted 2025-01-13 cs.LG cs.AI

ACCon: Angle-Compensated Contrastive Regularizer for Deep Regression

classification cs.LG cs.AI
keywords regressioncontrastiveangle-compensateddeeplearningregularizertasksexisting
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In deep regression, capturing the relationship among continuous labels in feature space is a fundamental challenge that has attracted increasing interest. Addressing this issue can prevent models from converging to suboptimal solutions across various regression tasks, leading to improved performance, especially for imbalanced regression and under limited sample sizes. However, existing approaches often rely on order-aware representation learning or distance-based weighting. In this paper, we hypothesize a linear negative correlation between label distances and representation similarities in regression tasks. To implement this, we propose an angle-compensated contrastive regularizer for deep regression, which adjusts the cosine distance between anchor and negative samples within the contrastive learning framework. Our method offers a plug-and-play compatible solution that extends most existing contrastive learning methods for regression tasks. Extensive experiments and theoretical analysis demonstrate that our proposed angle-compensated contrastive regularizer not only achieves competitive regression performance but also excels in data efficiency and effectiveness on imbalanced datasets.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.