Xiaohan Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaohan Huang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Meng Xiao
Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and DUKE-NUS Medical School, National University of Singapore, Singapore, Singapore
4 shared publications - Yuanchun Zhou
Computer Network Information Center, Chinese Academy of Sciences, China
4 shared publications - Qingqing Long
Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of the Chinese Academy of Sciences, Beijing, China
3 shared publications - Hengshu Zhu
Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China
2 shared publications - Min Wu
Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR) , Singapore 138632
2 shared publications - Weiliang Zhang
Computer Network Information Center, Chinese Academy of Sciences, Beijing, China
2 shared publications
Latest Publications
- Open Access
- 11 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
Trajectory-Constrained Feature Transformation Optimization Framework for Stable Tabular Data Reprogramming
Tabular data reprogramming is a cornerstone of Data-Centric AI, which seeks to mathematically reconfigure raw features into more expressive and model-efficient representations. This process has traditionally relied on extensive manual engineering. Further, recent automated feature transformation approaches treat each transformation as conditionally independent, preventing the reuse of successful exploration experiences and learning from failures. This myopic view results in redundant evaluations, unstable exploration, and limited generalizability. To address the limitations, we propose the Trajectory-Constrained Transformation Optimization ( TCTO ), a novel data reprogramming framework that reconceptualizes feature transformation as a coordinated planning problem rather than isolated optimization steps. TCTO introduces a cascading multi-agent reinforcement learning (MARL) system that maintains an evolving roadmap where features become nodes and transformations form edges. This framework supports three critical capabilities: (1) trajectory-aware planning with intelligent backtracking from local optima, (2) reuse of previously generated intermediate features, and (3) localized contribution tracking that stabilizes the exploration process. During agent learning, experience replay reuses stored transitions and rewards, avoiding repeated downstream-model evaluations for the sampled experiences. Extensive experiments and case studies across diverse benchmark datasets and tasks demonstrate that TCTO achieves superior performance, stability, and traceability, advancing the DCAI paradigm toward intelligent systems that learn not only from data, but to reprogram data itself. 1
- 11 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
Open AccessTrajectory-Constrained Feature Transformation Optimization Framework for Stable Tabular Data Reprogramming
Tabular data reprogramming is a cornerstone of Data-Centric AI, which seeks to mathematically reconfigure raw features into more expressive and model-efficient representations. This process has traditionally relied on extensive manual engineering. Further, recent automated feature transformation approaches treat each transformation as conditionally independent, preventing the reuse of successful exploration experiences and learning from failures. This myopic view results in redundant evaluations, unstable exploration, and limited generalizability. To address the limitations, we propose the Trajectory-Constrained Transformation Optimization ( TCTO ), a novel data reprogramming framework that reconceptualizes feature transformation as a coordinated planning problem rather than isolated optimization steps. TCTO introduces a cascading multi-agent reinforcement learning (MARL) system that maintains an evolving roadmap where features become nodes and transformations form edges. This framework supports three critical capabilities: (1) trajectory-aware planning with intelligent backtracking from local optima, (2) reuse of previously generated intermediate features, and (3) localized contribution tracking that stabilizes the exploration process. During agent learning, experience replay reuses stored transitions and rewards, avoiding repeated downstream-model evaluations for the sampled experiences. Extensive experiments and case studies across diverse benchmark datasets and tasks demonstrate that TCTO achieves superior performance, stability, and traceability, advancing the DCAI paradigm toward intelligent systems that learn not only from data, but to reprogram data itself. 1
- Open Access
- 5 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (8) , 1-25
Comprehend, Divide, and Conquer: Feature Subspace Exploration via Multi-Agent Hierarchical Reinforcement Learning
Feature selection aims to preprocess the target dataset, find an optimal and most streamlined feature subset, and enhance the downstream machine learning task. Among filter, wrapper, and embedded-based approaches, the reinforcement learning (RL)-based subspace exploration strategy provides a novel objective optimization-directed perspective and promising performance. Nevertheless, even with improved performance, current reinforcement learning approaches face challenges similar to conventional methods when dealing with complex datasets. These challenges stem from the inefficient paradigm of using one-agent-per-feature and the inherent complexities present in the datasets. This observation motivates us to investigate and address the above issue and propose a novel approach, namely HRLFS . Our methodology initially employs a Large Language Model (LLM)-based hybrid state extractor to capture each feature’s mathematical and semantic characteristics. Based on this information, features are clustered, facilitating the construction of hierarchical agents for each cluster and sub-cluster. Extensive experiments demonstrate the efficiency, scalability, and robustness of our approach. Compared to contemporary or one-feature-one-agent RL-based approaches, HRLFS improves the downstream ML performance with iterative feature subspace exploration while accelerating total runtime by reducing the number of agents involved. Our code and dataset are publicly accessible on GitHub and Huggingface .
- 5 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (8) , 1-25
Open AccessComprehend, Divide, and Conquer: Feature Subspace Exploration via Multi-Agent Hierarchical Reinforcement Learning
Feature selection aims to preprocess the target dataset, find an optimal and most streamlined feature subset, and enhance the downstream machine learning task. Among filter, wrapper, and embedded-based approaches, the reinforcement learning (RL)-based subspace exploration strategy provides a novel objective optimization-directed perspective and promising performance. Nevertheless, even with improved performance, current reinforcement learning approaches face challenges similar to conventional methods when dealing with complex datasets. These challenges stem from the inefficient paradigm of using one-agent-per-feature and the inherent complexities present in the datasets. This observation motivates us to investigate and address the above issue and propose a novel approach, namely HRLFS . Our methodology initially employs a Large Language Model (LLM)-based hybrid state extractor to capture each feature’s mathematical and semantic characteristics. Based on this information, features are clustered, facilitating the construction of hierarchical agents for each cluster and sub-cluster. Extensive experiments demonstrate the efficiency, scalability, and robustness of our approach. Compared to contemporary or one-feature-one-agent RL-based approaches, HRLFS improves the downstream ML performance with iterative feature subspace exploration while accelerating total runtime by reducing the number of agents involved. Our code and dataset are publicly accessible on GitHub and Huggingface .
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9137-9148
SciHorizon-Gene: Benchmarking LLM for Life Sciences Inference from Gene Knowledge to Functional Understanding
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9137-9148
Open AccessSciHorizon-Gene: Benchmarking LLM for Life Sciences Inference from Gene Knowledge to Functional Understanding
- 1 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Biology and Bioinformatics
- Vol. 22 (6) , 3041-3054
Knowledge-Guided Gene Panel Selection for Label-Free Single-Cell RNA-Seq Data: A Reinforcement Learning Perspective
Gene panel selection aims to identify the most informative genomic biomarkers in label-free genomic datasets. Traditional approaches, which rely on domain expertise, embedded machine learning models, or heuristic-based iterative optimization, often introduce biases and inefficiencies, potentially obscuring critical biological signals. To address these challenges, we present an iterative gene panel selection strategy that harnesses ensemble knowledge from existing gene selection algorithms to establish preliminary boundaries or prior knowledge, which guide the initial search space. Subsequently, we incorporate reinforcement learning (RL) through a reward function shaped by expert behavior, enabling dynamic refinement and targeted selection of gene panels. This integration mitigates biases stemming from initial boundaries while capitalizing on RL's stochastic adaptability. Comprehensive comparative experiments, case studies, and downstream analyses demonstrate the effectiveness of our method, highlighting its improved precision and efficiency for label-free biomarker discovery. Our results underscore the potential of this approach to advance single-cell genomics data analysis.
- 1 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Biology and Bioinformatics
- Vol. 22 (6) , 3041-3054
Knowledge-Guided Gene Panel Selection for Label-Free Single-Cell RNA-Seq Data: A Reinforcement Learning Perspective
Gene panel selection aims to identify the most informative genomic biomarkers in label-free genomic datasets. Traditional approaches, which rely on domain expertise, embedded machine learning models, or heuristic-based iterative optimization, often introduce biases and inefficiencies, potentially obscuring critical biological signals. To address these challenges, we present an iterative gene panel selection strategy that harnesses ensemble knowledge from existing gene selection algorithms to establish preliminary boundaries or prior knowledge, which guide the initial search space. Subsequently, we incorporate reinforcement learning (RL) through a reward function shaped by expert behavior, enabling dynamic refinement and targeted selection of gene panels. This integration mitigates biases stemming from initial boundaries while capitalizing on RL's stochastic adaptability. Comprehensive comparative experiments, case studies, and downstream analyses demonstrate the effectiveness of our method, highlighting its improved precision and efficiency for label-free biomarker discovery. Our results underscore the potential of this approach to advance single-cell genomics data analysis.