Latest Semi-Supervised Learning Research Papers

The newest Semi-Supervised Learning papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Semi-Supervised Learning so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• A semi-supervised compound fault diagnosis method based on hierarchical attention and self-supervised graph learning for the rotary components of robots’ joints
  Zida Zhao, Chengshang Si, Shilong Sun, Dong Wang et al. · Mechanical Systems and Sign... · Sep 10, 2026
• Human-in-the-Loop Data Science: Enhancing Model Performance Through Interactive Learning Mechanisms
  Isnawijayani ., Elmar B. Noche, Yamini Sood, Dinesh Kumar · Journal of Data Sciences · Sep 10, 2026

  Purely automated machine learning systems often struggle to incorporate domain knowledge and contextual reasoning, resulting in reduced performance when handling ambiguous, noisy, or complex real-world data. Although existing approaches suc…

• Stellar characterization with photometric colors from J-PLUS and 2MASS surveys
  J. F. Aguilar, P. Cruz, E. Solano, P. R. T. Coelho et al. · Astronomy and Astrophysics · Sep 9, 2026

  We aim at deriving stellar atmospheric parameters based on the photometric data from the Javalambre Photometric Local Universe Survey (J-PLUS) in addition to near-infrared photometry from the Two Micron All-Sky Survey (2MASS). Our method co…

• Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation
  Jiacheng Xu, Feng Chen, Xiuneng Xu, Bo An · arXiv · Sep 8, 2026

  Existing methods for test-time reinforcement learning (TTRL) derive rewards from answer-level self-voting on unlabeled test-time tasks with canonical answers, but this breaks down for code generation because programs cannot be compared by s…

• Predicting the status of 35 sustainable development goal indicators in Indian villages: a semi-supervised machine learning approach for precision public policy
  Soohyeon Ko, Avleen S. Bijral, Abhimanyu Singh, Jeffrey C. Blossom et al. · The Lancet Regional Health ... · Sep 8, 2026

  Background National and district-level monitoring of the Sustainable Development Goals (SDGs) in India obscures substantial inequalities at finer geographic resolutions, such as villages. While villages are central to service delivery and l…

• Alternative learning with semi-supervised relaxation for alternating-current optimal power flow
  Hien Thanh Doan, Keunju Song, Sungho Shin, Kibaek Kim et al. · Engineering Applications of... · Sep 8, 2026
• Curriculum-based inter-modality contrastive learning for semi-supervised cross-modal retrieval
  Man Wu, Dizhan Xue, Yang Yang, Jing Fang et al. · Multimedia Systems · Sep 6, 2026
• LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style Updates
  Dmitrii Andriianov, Andrey Veprikov, Aleksandr Beznosikov · arXiv · Sep 2, 2026

  Low-rank adaptation (LoRA) is the standard way to fine-tune large models, yet when its two factors are trained independently, the update ignores the geometry of the low-rank weight change it induces. We introduce LoRA-TSD, an optimizer that…

• J-PAS: Semisupervised Sim-to-Obs Transfer for Robust Star–Galaxy–Quasar Classification
  Daniel López-Cano, L. Raul Abramo, L. Nakazono, I. Pérez-Ràfols et al. · The Astrophysical Journal · Sep 2, 2026

  Abstract Modern astrophysics and cosmology increasingly rely on simulations and cross-survey analyses, yet differences in instrumentation, calibration, and modeling introduce distribution mismatches between simulated and observed datasets (…

• Geometry-Guided Semi-Supervised Multimodal Segmentation for UAV-Based Rice-Lodging Mapping
  Zhongyuan Wang, 鍾幸珮, Zaorui Song, Sizhe Dai et al. · Remote Sensing · Sep 2, 2026

  Accurate rice-lodging mapping from unmanned aerial vehicle (UAV) imagery supports post-disaster loss assessment, crop insurance, and precision field management. Existing deep-learning methods typically require dense pixel-level annotations,…

• Semi-supervised Retrieval of Functional Residues Through the Integration of Protein Language Models and Gene Ontology Data
  Andrew Dickson, Salma Mouline, Ali Tamadon, Mohammad R. K. Mofrad · Bioinformatics · Aug 31, 2026

  Abstract Motivation Experimental studies of protein function often focus on mechanistic descriptions, characterizing how specific sites and residues contribute to activity. Abstractions such as domains and active sites enable quantitative d…

• Sparse weakly semi-supervised learning for oriented ship detection in polarimetric SAR images
  Yucong He, Gui Gao, Tianwen Zhang, Dunyun He · ISPRS Journal of Photogramm... · Aug 25, 2026
• Diversity-Based Active Learning: An Evaluation of Metric Spaces for Active Learning Selection
  Siddharth Chilamkur, Dorit S. Hochbaum · arXiv · Aug 24, 2026

  With rapid advancement over the last few years, many different methods are now widely used for classification. However, training these models requires substantial labeled data. Active Learning is a potential solution to this problem. Pool-b…

• PortMatch: A semi-supervised semantic segmentation framework for belt conveyor inspection in ports
  Guanke Chen, Chan Jia, Haibin Li, Yaqian Li et al. · Engineering Applications of... · Aug 22, 2026
• A data-driven semi-supervised framework with adaptive quality filtering for imbalanced binary image classification
  M. S. Neethu, S. S. Vinod Chandra · International Journal of Da... · Aug 20, 2026
• On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification
  Qinyuan Ye, Yu Li, Yada Pruksachatkun, Jiaxin Zhang et al. · arXiv · Aug 18, 2026

  Memory-based self-improving agents--those that learn from an online stream of tasks and improve over time by maintaining a textual memory bank--have shown great promise in recent literature. However, the reliability aspects of these methods…

• Semi-supervised domain-adaptation-driven transfer learning for strength prediction of waste-derived concrete using physicochemical–mechanical knowledge–information
  Laren Satpathy, Suraj Kumar Parhi, Sanjaya Kumar Patro, Amar Nath Nayak · Advanced Engineering Inform... · Aug 18, 2026
• Learning Geometric Information Propagation for Semi-supervised 3D Medical Image Segmentation
  Lianyuan Yu, Xiuzhen Guo, Ji Shi, Hongxiao Wang et al. · Journal of Imaging Informat... · Aug 10, 2026
• Bidirectional cross-view learning with dynamic region selection for semi-supervised medical image segmentation
  Jiangxiong Fang, Hao Luo, Haihuai Zeng, Jie Jin et al. · Complex & Intelligent Systems · Jul 18, 2026

  Semi-supervised medical image segmentation aims to alleviate the heavy reliance on dense annotations while preserving high segmentation accuracy, yet it remains challenging due to unreliable pseudo-labels and insufficient utilization of unl…

• SSTEAD-net: A semi-supervised temporal encoding and adaptive denoising network for effluent soft sensing in wastewater treatment plants
  Toqeer Ahmed, Awais Khan Jumani, Aftab ul Nabi, Kamlesh et al. · Journal of Water Process En... · Jul 17, 2026
• A semi-supervised tool wear monitoring approach integrating physics-guided weak labels and uncertainty quantification
  Yezhen Peng, Fengwen Yu, Weimin Kang, Nanjie Han et al. · Mechanical Systems and Sign... · Jul 16, 2026
• Explainable Semi-Supervised Learning Framework for Alzheimer’s Disease Prediction Using SHAP-Based Feature Selection and Cost-Sensitive CatBoost
  Abdallah El Chakik, Bilal Nakhal, Ghalia Nassreddine · Sci · Jul 15, 2026

  Alzheimer’s disease (AD) remains a critical global health challenge for which early diagnosis is essential for effective intervention. However, AD detection is a challenging and complex task due to the scarcity of labeled clinical data, cla…

• Distribution-aware probability contrastive learning for class-imbalanced semi-supervised learning
  Pengfei Lv, Jing Chai · OpenAlex · Jul 13, 2026

  Semi-Supervised Learning (SSL) has shown significant advantages by leveraging abundant unlabeled data to enhance model performance with successful applications in computer vision. However, existing SSL methods might exhibit significant perf…

• Semi-Supervised Learning for Molecular Graphs via Ensemble Consensus
  Rasmus Hannibal Tirsgaard, Laurits Fredsgaard, Marisa Wodrich, Mikkel Jordahn et al. · ICML 2026 regular · Apr 30, 2026

  Machine learning is transforming molecular sciences by accelerating property prediction, simulation, and the discovery of new molecules and materials. Acquiring labeled data in these domains is often costly and time-consuming, whereas large…

• Newton-coupled Dual-Teacher Semi-supervised Learning Framework
  Hongyang He, Xinyuan Song, Yan Zhong, Daizong Liu et al. · ICML 2026 regular · Apr 30, 2026

  Most semi-supervised learning frameworks rely on a single teacher that transfers zero-order supervision through pseudo-labels, constraining the student to imitate categorical outputs without perceiving the loss geometry. This design often l…

• In Context Semi-Supervised Learning
  Jiashuo Fan, Paul Rosu, Aaron T Wang, Lawrence Carin et al. · ICLR 2026 Poster · Jan 26, 2026

  There has been significant recent interest on understanding the capacity of Transformers for in-context learning (ICL), yet most theory focuses on supervised settings with explicitly labeled pairs. In practice, Transformers often perform we…

• Informative missingness and its implications in semi-supervised learning
  Jinran Wu, You‐Gan Wang, Geoffrey J. McLachlan · The Innovation Informatics · Dec 4, 2025

  Semi-supervised learning (SSL) constructs classifiers using both labelled and unlabelled data. It leverages information from labelled samples, whose acquisition is often costly or labour-intensive, together with unlabelled data to enhance p…

• Advanced fault diagnosis in milling cutting tools using vision transformers with semi-supervised learning and uncertainty quantification
  Muhammad Farooq Siddique, Muhammad Umar, Wasim Ahmad, Jong-Myon Kim · Scientific Reports · Nov 27, 2025

  This study proposes a semi-supervised fault diagnosis framework based on vision transformers (ViTs) to enhance the diagnostic accuracy and generalization in machine cutting tools (MCT), particularly under the constraint of limited labeled d…

• Active semi-supervised learning for multi-target regression
  Maira Farias Andrade Lira, Luisa Cavalcante, Celine Vens, Ricardo Prudencio et al. · BNAIC/BeNeLearn 2025 Oral · Oct 15, 2025

  Recent works have proposed the combination of active and semi-supervised learning techniques to efficiently incorporate unlabeled data. The so-called active semi-supervised learning (ASSL) investigates methods to efficiently construct predi…

• Semi-Supervised Contrastive Learning with Orthonormal Prototypes
  Huanran Li, Manh Nguyen, Daniel L. Pimentel-Alarcón · Submitted to ICLR 2026 · Sep 19, 2025

  Contrastive learning has emerged as a powerful method in deep learning, excelling at learning effective representations through contrasting samples from different distributions. However, dimensional collapse, where embeddings converge into …