Hao-Yuan He
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hao-Yuan He has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Ming Li
Nanjing University
6 shared publications - Wang-Zhou Dai
Nanjing University
2 shared publications - Zheng Xie
National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, Nanjing, China
2 shared publications - Hui Sun
National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, Nanjing, China
1 shared publication - Ren-Biao Liu
National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China
1 shared publication - Yan-Xiao Huang
Nanjing University
1 shared publication
Latest Publications
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (7) , 8485-8502
Mitigating Negative Transfer via Reducing Environmental Disagreement
Unsupervised Domain Adaptation (UDA) focuses on transferring knowledge from a labeled source domain to an unlabeled target domain, addressing the challenge of domain shift. Significant domain shifts hinder effective knowledge transfer, leading to negative transfer and deteriorating model performance. Therefore, mitigating negative transfer is essential. This study revisits negative transfer through the lens of causally disentangled learning, emphasizing cross-domain discriminative disagreement on non-causal environmental features as a critical factor. Our theoretical analysis reveals that overreliance on non-causal environmental features as the environment evolves can cause discriminative disagreements (termed environmental disagreement), thereby resulting in negative transfer. To address this, we propose Reducing Environmental Disagreement (RED), which disentangles each sample into domain-invariant causal features and domain-specific non-causal environmental features via adversarially training domain-specific environmental feature extractors in the opposite domains. Subsequently, RED estimates and reduces environmental disagreement based on domain-specific non-causal environmental features. Experimental results confirm that RED effectively mitigates negative transfer and achieves state-of-the-art performance.
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (7) , 8485-8502
Mitigating Negative Transfer via Reducing Environmental Disagreement
Unsupervised Domain Adaptation (UDA) focuses on transferring knowledge from a labeled source domain to an unlabeled target domain, addressing the challenge of domain shift. Significant domain shifts hinder effective knowledge transfer, leading to negative transfer and deteriorating model performance. Therefore, mitigating negative transfer is essential. This study revisits negative transfer through the lens of causally disentangled learning, emphasizing cross-domain discriminative disagreement on non-causal environmental features as a critical factor. Our theoretical analysis reveals that overreliance on non-causal environmental features as the environment evolves can cause discriminative disagreements (termed environmental disagreement), thereby resulting in negative transfer. To address this, we propose Reducing Environmental Disagreement (RED), which disentangles each sample into domain-invariant causal features and domain-specific non-causal environmental features via adversarially training domain-specific environmental feature extractors in the opposite domains. Subsequently, RED estimates and reduces environmental disagreement based on domain-specific non-causal environmental features. Experimental results confirm that RED effectively mitigates negative transfer and achieves state-of-the-art performance.
- 7 June 2026
- Published by Springer Nature
- p. 393-404
Tri-ABL: Enhancing ABL Using Three Learners
- 17 March 2025
- Published by Springer Nature in Machine Learning
- Vol. 114 (5) , 1-20
Probabilistic instance dependent label refinement for noisy label learning
- 17 March 2025
- Published by Springer Nature in Machine Learning
- Vol. 114 (5) , 1-20
Probabilistic instance dependent label refinement for noisy label learning
- 30 January 2024
- Published by Springer Nature in Machine Learning
- Vol. 113 (6) , 3357-3377
Reduced implication-bias logic loss for neuro-symbolic learning
- 30 January 2024
- Published by Springer Nature in Machine Learning
- Vol. 113 (6) , 3357-3377
Reduced implication-bias logic loss for neuro-symbolic learning
- 24 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (7) , 4780-4795
Weakly Supervised AUC Optimization: A Unified Partial AUC Approach
Since acquiring perfect supervision is usually difficult, real-world machine learning tasks often confront inaccurate, incomplete, or inexact supervision, collectively referred to as weak supervision. In this work, we present WSAUC, a unified framework for weakly supervised AUC optimization problems, which covers noisy label learning, positive-unlabeled learning, multi-instance learning, and semi-supervised learning scenarios. Within the WSAUC framework, we first frame the AUC optimization problems in various weakly supervised scenarios as a common formulation of minimizing the AUC risk on contaminated sets, and demonstrate that the empirical risk minimization problems are consistent with the true AUC. Then, we introduce a new type of partial AUC, specifically, the reversed partial AUC (rpAUC), which serves as a robust training objective for AUC maximization in the presence of contaminated labels. WSAUC offers a universal solution for AUC optimization in various weakly supervised scenarios by maximizing the empirical rpAUC. Theoretical and experimental results under multiple settings support the effectiveness of WSAUC on a range of weakly supervised AUC optimization tasks.
- 24 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (7) , 4780-4795
Weakly Supervised AUC Optimization: A Unified Partial AUC Approach
Since acquiring perfect supervision is usually difficult, real-world machine learning tasks often confront inaccurate, incomplete, or inexact supervision, collectively referred to as weak supervision. In this work, we present WSAUC, a unified framework for weakly supervised AUC optimization problems, which covers noisy label learning, positive-unlabeled learning, multi-instance learning, and semi-supervised learning scenarios. Within the WSAUC framework, we first frame the AUC optimization problems in various weakly supervised scenarios as a common formulation of minimizing the AUC risk on contaminated sets, and demonstrate that the empirical risk minimization problems are consistent with the true AUC. Then, we introduce a new type of partial AUC, specifically, the reversed partial AUC (rpAUC), which serves as a robust training objective for AUC maximization in the presence of contaminated labels. WSAUC offers a universal solution for AUC optimization in various weakly supervised scenarios by maximizing the empirical rpAUC. Theoretical and experimental results under multiple settings support the effectiveness of WSAUC on a range of weakly supervised AUC optimization tasks.
- Open Access
Reduced Implication-bias Logic Loss for Neuro-Symbolic Learning
Integrating logical reasoning and machine learning by approximating logical inference with differentiable operators is a widely used technique in Neuro-Symbolic systems. However, some differentiable operators could bring a significant bias during backpropagation and degrade the performance of Neuro-Symbolic learning. In this paper, we reveal that this bias, named \textit{Implication Bias} is common in loss functions derived from fuzzy logic operators. Furthermore, we propose a simple yet effective method to transform the biased loss functions into \textit{Reduced Implication-bias Logic Loss (RILL)} to address the above problem. Empirical study shows that RILL can achieve significant improvements compared with the biased logic loss functions, especially when the knowledge base is incomplete, and keeps more robust than the compared methods when labelled data is insufficient.
Open AccessReduced Implication-bias Logic Loss for Neuro-Symbolic Learning
Integrating logical reasoning and machine learning by approximating logical inference with differentiable operators is a widely used technique in Neuro-Symbolic systems. However, some differentiable operators could bring a significant bias during backpropagation and degrade the performance of Neuro-Symbolic learning. In this paper, we reveal that this bias, named \textit{Implication Bias} is common in loss functions derived from fuzzy logic operators. Furthermore, we propose a simple yet effective method to transform the biased loss functions into \textit{Reduced Implication-bias Logic Loss (RILL)} to address the above problem. Empirical study shows that RILL can achieve significant improvements compared with the biased logic loss functions, especially when the knowledge base is incomplete, and keeps more robust than the compared methods when labelled data is insufficient.