Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer
National University of Singapore（新加坡国立大学）；University of Electronic Science and Technology of China（电子科技大学）；Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）；The Hong Kong University of Science and Technology（香港科技大学）；Singapore Institute of Manufacturing Technology, A*STAR（新加坡科技研究局新加坡制造技术研究院）；Shandong University（山东大学）
Accepted at NeurIPS 2021. Changes in v3: updated CVRP performance due to more accurate feasibility masks (reduced training time); improved comparison analysis in Table 1 and Section 5; fixed minor typos/inaccuracies in the CPE equation, Figure 6, and other sentences
Recently, Transformer has become a prevailing deep architecture for solving vehicle routing problems (VRPs). However, it is less effective in learning improvement models for VRP because its positional encoding (PE) method is not suitable in representing VRP solutions. This paper presents a novel Dual-Aspect Collaborative Transformer (DACT) to learn embeddings for the node and positional features separately, instead of fusing them together as done in existing ones, so as to avoid potential noises and incompatible correlations. Moreover, the positional features are embedded through a novel cyclic positional encoding (CPE) method to allow Transformer to effectively capture the circularity and symmetry of VRP solutions (i.e., cyclic sequences). We train DACT using Proximal Policy Optimization and design a curriculum learning strategy for better sample efficiency. We apply DACT to solve the traveling salesman problem (TSP) and capacitated vehicle routing problem (CVRP). Results show that our DACT outperforms existing Transformer based improvement models, and exhibits much better generalization performance across different problem sizes on synthetic and benchmark instances, respectively.
Collaboration! Towards Robust Neural Methods for Routing Problems
Nanyang Technological University（南洋理工大学）；Eindhoven University of Technology（埃因霍温理工大学）；Singapore Management University（新加坡管理大学）；Shandong University（山东大学）
CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing
The University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；Intel（英特尔）；Carnegie Mellon University（卡内基梅隆大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·拉希德人工智能大学）；Rutgers University（罗格斯大学）
A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning
UNC-Chapel Hill（北卡罗来纳大学教堂山分校）；University of Toronto（多伦多大学）；Vector Institue（向量研究所）；MIT（麻省理工学院）；MIT-IBM Watson AI Lab（麻省理工-IBM沃森人工智能实验室）；Microsoft Research（微软研究院）；Mila（蒙特利尔人工智能研究院）
Adaptive Collaborative Similarity Learning for Unsupervised Multi-view Feature Selection
Shandong Normal University（山东师范大学）；Shandong University（山东大学）；University of Electronic Science and Technology of China（电子科技大学）；National University of Singapore（新加坡国立大学）
