Pith. sign in

REVIEW 6 cited by

SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised 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 2301.10921 v2 pith:MLZJMBUZ submitted 2023-01-26 cs.LG cs.AIcs.CV

SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning

classification cs.LG cs.AIcs.CV
keywords datalearningsoftmatchtrade-offconfidenceeffectivelyhighpseudo-labeling
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited labeled data and massive unlabeled data to improve the model's generalization performance. In this paper, we first revisit the popular pseudo-labeling methods via a unified sample weighting formulation and demonstrate the inherent quantity-quality trade-off problem of pseudo-labeling with thresholding, which may prohibit learning. To this end, we propose SoftMatch to overcome the trade-off by maintaining both high quantity and high quality of pseudo-labels during training, effectively exploiting the unlabeled data. We derive a truncated Gaussian function to weight samples based on their confidence, which can be viewed as a soft version of the confidence threshold. We further enhance the utilization of weakly-learned classes by proposing a uniform alignment approach. In experiments, SoftMatch shows substantial improvements across a wide variety of benchmarks, including image, text, and imbalanced classification.

discussion (0)

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

Forward citations

Cited by 6 Pith papers

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

  1. Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning

    cs.CV 2026-06 unverdicted novelty 6.0

    GGR is a gradient-space projection technique that rectifies auxiliary updates in open-set SSL to avoid first-order opposition with supervised learning while retaining orthogonal signals.

  2. Can LLMs Learn to Reason Robustly under Noisy Supervision?

    cs.LG 2026-04 conditional novelty 6.0

    Online Label Refinement lets LLMs learn robust reasoning from noisy supervision by correcting labels when majority answers show rising rollout success and stable history, delivering 3-4% gains on math and reasoning be...

  3. APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms

    cs.CV 2026-06 unverdicted novelty 5.0

    APRIL-MedSeg is a new open-source modular toolbox that uses YAML configuration and component registries to unify multiple advanced paradigms for medical image segmentation.

  4. GeoMin: Data-Efficient Semi-Supervised RLVR via Geometric Distribution Modeling

    cs.LG 2026-06 unverdicted novelty 5.0

    GeoMin uses geometric distribution modeling on labeled data to assess self-reward reliability, enabling better performance in semi-supervised RLVR with only 10% of typical annotations.

  5. PRISM: Prioritized Channel Importance with Semi-supervised Domain Adaptation for Cross-Subject EEG Emotion Recognition

    cs.LG 2026-07 unverdicted novelty 4.0

    PRISM combines data-dependent channel weighting via expert ensemble and confidence-filtered pseudo-label domain adaptation to outperform prior methods on cross-subject EEG emotion tasks in DEAP, DREAMER, and SEED.

  6. APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms

    cs.CV 2026-06 unverdicted novelty 4.0

    Presents APRIL-MedSeg, a modular YAML-configurable toolbox for 2D medical image segmentation integrating semi-supervised, domain adaptation, distillation, weakly supervised, text-guided, and foundation model paradigms...