The constructive approach within Neural Combinatorial Optimization (NCO) treats a combinatorial optimization problem as a finite Markov decision process, where solutions are built incrementally through a sequence of decisions guided by a neural policy network. To train the policy, recent research is shifting toward a 'self-improved' learning methodology that addresses the limitations of reinforcement learning and supervised approaches. Here, the policy is iteratively trained in a supervised manner, with solutions derived from the current policy serving as pseudo-labels. The way these solutions are obtained from the policy determines the quality of the pseudo-labels. In this paper, we present a simple and problem-independent sequence decoding method for self-improved learning based on sampling sequences without replacement. We incrementally follow the best solution found and repeat the sampling process from intermediate partial solutions. By modifying the policy to ignore previously sampled sequences, we force it to consider only unseen alternatives, thereby increasing solution diversity. Experimental results for the Traveling Salesman and Capacitated Vehicle Routing Problem demonstrate its strong performance. Furthermore, our method outperforms previous NCO approaches on the Job Shop Scheduling Problem.
Projecting Latent RL Actions: Towards Generalizable and Scalable Graph Combinatorial Optimization
Université de Lorraine, CNRS, Inria, LORIA(洛林大学、国家科学研究中心、法国国家信息与自动化研究所、LORIA实验室);University of California Santa Barbara(加州圣芭芭拉大学);Universitat Politècnica de Catalunya(加泰罗尼亚理工大学)
Task-Aware Calibration: Provably Optimal Decoding in LLMs
School of Computation, Information & Technology, Technical University of Munich(慕尼黑技术大学计算、信息与技术学院);Munich Data Science Institute(慕尼黑数据科学研究所);Munich Center for Machine Learning(慕尼黑机器学习中心);University of Amsterdam(阿姆斯特丹大学)
WeCon: An Efficient Weight-Conditioned Neural Solver for Multi-Objective Combinatorial Optimization Problems
Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education(教育部符号计算与知识工程重点实验室);College of Computer Science and Technology, Jilin University(吉林大学计算机科学与技术学院);Department of Industrial Systems Engineering and Management, National University of Singapore(新加坡国立大学工业系统工程与管理系);College of Software, Jilin University(吉林大学软件学院);School of Software, Tsinghua University(清华大学软件学院);School of Computing and Information Systems, Singapore Management University(新加坡管理学院 computing and information systems 系)
LMask: Learn to Solve Constrained Routing Problems with Lazy Masking
Beijing International Center for Mathematical Research, Peking University(北京大学北京国际数学研究中心);Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院);Department of Statistics and Data Science, University of Pennsylvania(宾夕法尼亚大学统计与数据科学系)