18 citations · 20 across the 3 of their papers we have counts for
5 papers
Towards Practical Explainability with Cluster Descriptors
Xiaoyuan Liu, Ilya Tyagin, Hayato Ushijima-Mwesigwa +2
With the rapid development of machine learning, improving its explainability has become a crucial research goal. We study the problem of making the clusters more explainable by inv…
Partitioning Dense Graphs with Hardware Accelerators
Xiaoyuan Liu, Hayato Ushijima-Mwesigwa, Indradeep Ghosh +1
Graph partitioning is a fundamental combinatorial optimization problem that attracts a lot of attention from theoreticians and practitioners due to its broad applications. From mul…
Transferability of optimal QAOA parameters between random graphs
Alexey Galda, Xiaoyuan Liu, Danylo Lykov +2
The Quantum approximate optimization algorithm (QAOA) is one of the most promising candidates for achieving quantum advantage through quantum-enhanced combinatorial optimization. I…
Structured Hierarchical Dialogue Policy with Graph Neural Networks
Zhi Chen, Xiaoyuan Liu, Lu Chen +1
Dialogue policy training for composite tasks, such as restaurant reservation in multiple places, is a practically important and challenging problem. Recently, hierarchical deep rei…
Leveraging Special-Purpose Hardware for Local Search Heuristics
Xiaoyuan Liu, Hayato Ushijima-Mwesigwa, Avradip Mandal +3
As we approach the physical limits predicted by Moore's law, a variety of specialized hardware is emerging to tackle specialized tasks in different domains. Within combinatorial op…