20 results for “semi-supervised learning”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper presents MOEA-SSL, a multi-objective evolutionary approach for lightweight semi-supervised tabular classification.
This paper proposes a semi-supervised framework, RepG, for conditional generative modeling using stochastic interpolation and low-dimensional latent representations.
The paper proposes SEED, a novel semantic-structure-agnostic semi-supervised continual learning method that significantly improves malware detection performance under limited labeling by leveraging re…
Chengxi Deng, Xurong Xie, Shujie Hu, Jiajun Deng +6 more
A novel confidence score guided incremental and speaker adaptive pseudo-labeling approach is proposed for semi-supervised elderly speech recognition.
The paper proposes a robust semi-supervised temporal learning framework for cloud intrusion detection that explicitly handles adversarial contamination and temporal drift in unlabeled network traffic,…
DecomposeRL introduces an accurate and traceable claim verification model by framing the decomposition process as an RL policy, achieving state-of-the-art performance with significantly fewer training…
Ethan Lin, Akanksha Sarkar, Ziang Liu, Kristin Branson +1 more
This paper introduces Agentic Semi-Supervised Learning (AgentSSL) that uses machine learning agents to automate pipeline design in semi-supervised settings.
The paper introduces Label-Augmented Conditional Diffusion (LACD), a method for learning complex conditional distributions using unlabeled data, and provides theoretical guarantees for its effectivene…
Zefang Liu, Chenyang Zhu, Sangwoo Cho, Xujun Peng +2 more
The paper introduces StreamHear, a semi-supervised pipeline for adapting pretrained streaming ASR models to domain-shifted target audio using fine-tuning and pseudo-labeling.
The paper proposes a semi-supervised framework for converting tabla audio into symbolic stroke sequences using sequence-level labelled and unlabelled recordings.
This paper proposes a novel estimator for the target linear coefficient in a partial linear model with black-box nuisance estimation and establishes its unimprovable error rate.
This paper presents Cohort Organized Learning (CoOL), a method for clustering data without explicit distance or similarity computations.
The paper studies the problem of learning a drifting concept in the presence of Massart noise and provides an efficient learner with improved error rate for margin-separable linear classifiers.
A new boosting algorithm that strong learns concept classes closed under O(log 1/γ)-XOR using O(log 1/ε) calls to a γ-advantage weak learner and additional samples, by connecting boosting with list-de…
This paper analyzes the poor performance of Meta-learning for Training-data Selection (MTS) and proposes that increasing the batch size and incorporating informative features can significantly improve…
This paper extends gradient boosting to functions of vector inputs using a simple algorithm with histogram-based decision trees.
This paper introduces a self-supervised framework for discovering novel, structured concepts from raw imagery without human annotation.
The paper introduces Inconsistency-Aware Minimization (IAM), a novel training objective that uses a label-free measure called local inconsistency to improve model generalization, particularly in semi-…