Papers › Dash: Semi-Supervised Learning with Dynamic Thresholding
Dash: Semi-Supervised Learning with Dynamic Thresholding
Yi Xu, Lei Shang, Jinxing Ye, Qi Qian, Yu-Feng Li, Baigui Sun, Hao Li, Rong Jin
While semi-supervised learning (SSL) has received tremendous attentions in many machine learning tasks due to its successful use of unlabeled data, existing SSL algorithms use either all unlabeled examples or the unlabeled examples with a fixed high-confidence prediction during the training progress. However, it is possible that too many correct/wrong pseudo labeled examples are eliminated/selected. In this work we develop a simple yet powerful framework, whose key idea is to select a subset of training examples from the unlabeled data when performing existing SSL methods so that only the unlabeled examples with pseudo labels related to the labeled data will be used to train models. The selection is performed at each updating iteration by only keeping the examples whose losses are smaller than a given threshold that is dynamically adjusted through the iteration. Our proposed approach, Dash, enjoys its adaptivity in terms of unlabeled data selection and its theoretical guarantee. Specifically, we theoretically establish the convergence rate of Dash from the view of non-convex optimization. Finally, we empirically demonstrate the effectiveness of the proposed method in comparison with state-of-the-art over benchmarks.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Semi-Supervised Image Classification | CIFAR-10, 250 Labels | Dash (RA) | Percentage error | 4.56±0.13 | #5 of 27 | Archive leaderboard | report |
| Semi-Supervised Image Classification | CIFAR-10, 4000 Labels | Dash (RA, ours) | Percentage error | 4.08±0.06 | #9 of 49 | Archive leaderboard | report |
| Semi-Supervised Image Classification | CIFAR-100, 2500 Labels | Dash (RA, WRN-28-8) | Percentage error | 27.18±0.21 | #13 of 16 | Archive leaderboard | report |
| Semi-Supervised Image Classification | CIFAR-100, 400 Labels | Dash (RA, WRN-28-8) | Percentage error | 44.76±0.96 | #18 of 21 | Archive leaderboard | report |
| Semi-Supervised Image Classification | CIFAR-100, 400 Labels | Dash (CTA, WRN-28-8) | Percentage error | 44.83±1.36 | #19 of 21 | Archive leaderboard | report |
| Semi-Supervised Image Classification | cifar-100, 10000 Labels | Dash (RA, WRN-28-8) | Percentage error | 21.97±0.14 | #13 of 29 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections