Haoyang Liu

Haoyang Liu

Auto-generated profile, based on publicly available information

Haoyang Liu

CAS Key Laboratory of Technology in GIPAS, University of Science and Technology of China, Hefei, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 April 2025
Verified
Conference Paper
Open access
WMWenyu Mao
Wenyu Mao
SLShuchang Liu
Shuchang Liu
HLHaoyang Liu
Haoyang Liu
HLHaozhe Liu
Haozhe Liu
XLXiang Li
Xiang Li
LHLantao Hu
Lantao Hu

14 July 2024
Verified
Conference Paper
Open access
HLHongyu Liu
Hongyu Liu
HLHaoyang Liu
Haoyang Liu
YKYufei Kuang
Yufei Kuang
JWJie Wang
Jie Wang
BLBin Li
Bin Li
Combinatorial optimization (CO) is one of the most fundamental mathematical models in real-world applications. Traditional CO solvers, such as Branch-and-Bound (B&B) solvers, heavily rely on expert-designed heuristics, which are reliable but require substantial manual tuning. Recent studies have leveraged deep learning (DL) models as an alternative to capture rich feature patterns for improved performance on GPU machines. Nonetheless, the drawbacks of high training and inference costs, as well as limited interpretability, severely hinder the adoption of DL methods in real-world applications. To address these challenges, we propose a novel deep symbolic optimization learning framework that combines their advantages. Specifically, we focus on the node selection module within B&B solvers---namely, deep symbolic optimization for node selection (Dso4NS). With data-driven approaches, Dso4NS guides the search for mathematical expressions within the high-dimensional discrete symbolic space and then incorporates the highest-performing mathematical expressions into a solver. The data-driven model captures the rich feature information in the input data and generates symbolic expressions, while the expressions deployed in solvers enable fast inference with high interpretability. Experiments demonstrate the effectiveness of Dso4NS in learning high-quality expressions, outperforming existing approaches on a CPU machine. Encouragingly, the learned CPU-based policies consistently achieve performance comparable to state-of-the-art GPU-based approaches.

1 June 2026 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
HLHaoyang Liu
Haoyang Liu
JWJie Wang
Jie Wang
YKYufei Kuang
Yufei Kuang
XLXijun Li
Xijun Li
YZYongdong Zhang
Yongdong Zhang
FWFeng Wu
Feng Wu
Machine learning has been successfully applied to accelerate Mixed-Integer Linear Programming (MILP) solvers. However, the learning-based solvers often suffer from severe performance degradation on unseen MILP instances due to the limited number of training instances and diversity of training distributions. To tackle this problem, we propose a novel data augmentation approach, called Adversarial Instance Augmentation, to promote the data diversity for learning-based branching modules in branch-and-bound (B&B) Solvers (AdaSolver). To generate diverse augmented instances, AdaSolver uses an augmentation policy to augment the structures of the bipartite graphs representing MILP instances. The major technical contribution is that AdaSolver formulates the non-differentiable learning problem of the augmentation policy as a contextual bandit problem, enabling efficient gradient-based adversarial training for the learning-based solver and augmentation policy. To the best of our knowledge, AdaSolver is the first general and effective framework for understanding and improving the generalization of both imitation-learning-based and reinforcement-learning-based B&B solvers. Experiments demonstrate that AdaSolver leads to a remarkable roughly 35% improvement in solving time over the B&B solver across various distributions. Moreover, AdaSolver significantly improves the sample efficiency by roughly 40% reduction in solving time compared to the competitive GNN branching baseline with only 1% of the training instances.