NCAGC: A Neighborhood Contrast Framework for Attributed Graph Clustering

2 code implementations • 16 Jun 2022 • Tong Wang, Guanyu Yang, Qijia He, Zhenquan Zhang, Junhua Wu

However, most existing methods 1) do not directly address the clustering task, since the representation learning and clustering process are separated; 2) depend too much on data augmentation, which greatly limits the capability of contrastive learning; 3) ignore the contrastive message for clustering tasks, which adversely degenerate the clustering results.

Clustering Contrastive Learning +4

Evolutionary Computation plus Dynamic Programming for the Bi-Objective Travelling Thief Problem

no code implementations • 7 Feb 2018 • Junhua Wu, Sergey Polyakovskiy, Markus Wagner, Frank Neumann

This research proposes a novel indicator-based hybrid evolutionary approach that combines approximate and exact algorithms.

Exact Approaches for the Travelling Thief Problem

1 code implementation • 1 Aug 2017 • Junhua Wu, Markus Wagner, Sergey Polyakovskiy, Frank Neumann

Many evolutionary and constructive heuristic approaches have been introduced in order to solve the Traveling Thief Problem (TTP).