Upper Bounding Barlow Twins: A Novel Filter for Multi-Relational Clustering
Xiaowei Qian, Bingheng Li, Zhao Kang
Abstract
Multi-relational clustering is a challenging task due to the fact that diverse semantic information conveyed in multi-layer graphs is difficult to extract and fuse. Recent methods integrate topology structure and node attribute information through graph filtering. However, they often use a low-pass filter without fully considering the correlation among multiple graphs. To overcome this drawback, we propose to learn a graph filter motivated by the theoretical analysis of Barlow Twins. We find that input with a negative semi-definite inner product provides a lower bound for Barlow Twins loss, which prevents it from reaching a better solution. We thus learn a filter that yields an upper bound for Barlow Twins. Afterward, we design a simple clustering architecture and demonstrate its state-of-the-art performance on four benchmark datasets. The source code is available at https://github.com/XweiQ/BTGF.
BibTeX
@article{Qian_Li_Kang_2024, title={Upper Bounding Barlow Twins: A Novel Filter for Multi-Relational Clustering}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/29383}, DOI={10.1609/aaai.v38i13.29383}, abstractNote={Multi-relational clustering is a challenging task due to the fact that diverse semantic information conveyed in multi-layer graphs is difficult to extract and fuse. Recent methods integrate topology structure and node attribute information through graph filtering. However, they often use a low-pass filter without fully considering the correlation among multiple graphs. To overcome this drawback, we propose to learn a graph filter motivated by the theoretical analysis of Barlow Twins. We find that input with a negative semi-definite inner product provides a lower bound for Barlow Twins loss, which prevents it from reaching a better solution. We thus learn a filter that yields an upper bound for Barlow Twins. Afterward, we design a simple clustering architecture and demonstrate its state-of-the-art performance on four benchmark datasets. The source code is available at https://github.com/XweiQ/BTGF.}, number={13}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Qian, Xiaowei and Li, Bingheng and Kang, Zhao}, year={2024}, month={Mar.}, pages={14660-14668} }