TL;DR
SMVPU first extracts reliable negative samples from the unlabeled set and assigns similarity-weighted values to the remaining unlabeled instances, and then incorporates multi-view representations to enhance feature compatibility and discriminability.
: Partial multi-label learning addresses scenarios where each instance is associated with a set of candidate labels that include both relevant and irrelevant ones. In practical scenarios, such label sets are often simultaneously incomplete and noisy, which severely hampers the ability of models to extract compact and discriminative features. To address these issues, we propose an integrated learning paradigm that simultaneously enhances feature compactness and improves robustness against label noise. Our method learns an adaptive fuzzy neighborhood graph to capture the intrinsic relationships among instances. The resulting graph enables reliable label propagation, which effectively rectifies incorrect annotations and infers missing labels. In addition, we introduce a feature disentanglement mechanism that isolates reliable label-related feature representations from spurious ones introduced by noisy supervision. By integrating feature learning and label refinement into a joint optimization process, the proposed approach achieves a synergistic improvement in both representation quality and label reliability. Extensive theoretical analysis and empirical studies on multiple benchmark datasets demonstrate that our framework consistently outperforms state-of-the-art methods in terms of accuracy, stability, and robustness to annotation noise.
Evaluating the performance of Greedy K-center across a variety of metric spaces shows that mapping unlabeled instances into a predictive probability space and weighting the result by entropy often dominates the other options for active learning selection with Greedy K-center.
C-Score, a compact framework that evaluates training behavior in three complementary spaces: prediction, feature representation, and optimization, suggests that clean accuracy alone is insufficient for evaluating SSL robustness in open-world environments, and that internal diagnostic signals are necessary for more reliable robustness assessment under unlabeled contamination.
Existing semi-supervised learning (SSL) methods rely predominantly on pseudo-labeling and consistency regularization to leverage unlabeled data, demonstrating significant performance improvements. However, we pinpoint that these methods suffer from a confidence-for-weighting issue, overvaluing high-confidence pseudo-labels while undervaluing low-confidence yet informative samples that are critical for robust generalization. In this paper, we introduce EntropyMatch, an entropy-driven SSL framework that redefines sample importance through prediction entropy rather than confidence alone. EntropyMatch employs a bidirectional weighting strategy: upward exploitation exploits reliable hard samples to refine decision boundaries while downward exploration cautiously explores uncertain ones to reduce noise. Additionally, EntropyMatch features an adaptive training mechanism that aligns with model maturity, shifting focus from safe exploration to strategic exploitation as training progresses. Experiments on eight benchmarks across various SSL tasks—spanning image classification, facial expression recognition, and human action recognition—validate EntropyMatch’s robustness and effectiveness. It consistently achieves state-of-the-art results, notably matching state-of-the-art LION’s performance on RAF-DB with just half the labeled data, demonstrating superior data efficiency and generalization.
Multi-label complementary label learning (MLCLL) is a weakly supervised paradigm that addresses multi-label learning (MLL) tasks using complementary labels (i.e., irrelevant labels) instead of relevant labels. Existing methods typically adopt an unbiased risk estimator (URE) under the assumption that complementary labels follow a uniform distribution. However, this assumption fails in real-world scenarios due to instance-specific annotation biases, making URE-based methods ineffective under such conditions. Furthermore, existing methods un-derutilize label correlations inherent in MLL. To address these limitations, we propose ComRank , a ranking loss framework for MLCLL, which encourages complementary labels to be ranked lower than non-complementary ones, thereby modeling pairwise label relationships. Theoretically, our surrogate loss ensures Bayes consistency under both uniform and biased cases. Experiments demonstrate the effectiveness of our method in MLCLL tasks. The code is available at https://github.com/JellyJamZhu/ComRank.
Multi-view clustering aims to integrate complementary information from diverse views; however, effectively improving clustering performance with limited supervision remains a significant challenge. Existing semi-supervised methods often fail to fully exploit sparse labeled data or lack effective mechanisms to propagate supervisory constraints across views. To address these limitations, we propose a novel semi-supervised multi-view clustering method based on concept factorization, termed DSCF. Specifically, DSCF establishes a unified framework that incorporates pointwise constraints to enforce clustering consistency for labeled samples, while a hypergraph-based pairwise constraint propagation strategy is employed to transfer supervisory information to unlabeled data. Furthermore, a cross-view iterative update scheme is designed to effectively align and fuse constraint information among different views. Extensive experiments on eight benchmark multi-view datasets demonstrate that DSCF consistently outperforms several relevant multi-view clustering methods, validating its effectiveness in leveraging limited labeled information to enhance clustering performance.