Hard Sample Aware Network for Contrastive Deep Graph Clustering
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (7) · 8914-8922
DOI: 10.1609/aaai.v37i7.26071 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Yue Liu und 9 weiteren Autor:innen. Die Arbeit wurde bisher 125-mal zitiert (Crossref).
Abstract (Originalsprache)
Contrastive deep graph clustering, which aims to divide nodes into disjoint groups via contrastive mechanisms, is a challenging research spot. Among the recent works, hard sample mining-based algorithms have achieved great attention for their promising performance. However, we find that the existing hard sample mining methods have two problems as follows. 1) In the hardness measurement, the important structural information is overlooked for similarity calculation, degrading the representativeness of the selected hard negative samples. 2) Previous works merely focus on the hard negative sample pairs while neglecting the hard positive sample pairs. Nevertheless, samples within the same cluster but with low similarity should also be carefully learned. To solve the problems, we propose a novel contrastive deep graph clustering method dubbed Hard Sample Aware Network (HSAN) by introducing a comprehensive similarity measure criterion and a general dynamic sample weighing strategy. Concretely, in our algorithm, the similarities between samples are calculated by considering both the attribute embeddings and the structure embeddings, better revealing sample relationships and assisting hardness measurement. Moreover, under the guidance of the carefully collected high-confidence clustering information, our proposed weight modulating function will first recognize the positive and negative samples and then dynamically up-weight the hard sample pairs while down-weighting the easy ones. In this way, our method can mine not only the hard negative samples but also the hard positive sample, thus improving the discriminative capability of the samples further. Extensive experiments and analyses demonstrate the superiority and effectiveness of our proposed method. The source code of HSAN is shared at https://github.com/yueliu1999/HSAN and a collection (papers, codes and, datasets) of deep graph clustering is shared at https://github.com/yueliu1999/Awesome-Deep-Graph-Clustering on Github.
Zitieren
APA
Liu, Y., Yang, X., Zhou, S., Liu, X., Wang, Z., Liang, K., Tu, W., Li, L., Duan, J., & Chen, C. (2023). Hard Sample Aware Network for Contrastive Deep Graph Clustering. Proceedings of the AAAI Conference on Artificial Intelligence, 37(7), 8914-8922. https://doi.org/10.1609/aaai.v37i7.26071
Vancouver
Liu Y, Yang X, Zhou S, Liu X, Wang Z, Liang K, et al. Hard Sample Aware Network for Contrastive Deep Graph Clustering. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(7):8914-8922. doi:10.1609/aaai.v37i7.26071
BibTeX
@article{Liu2023,
author = {Liu, Yue and Yang, Xihong and Zhou, Sihang and Liu, Xinwang and Wang, Zhen and Liang, Ke and Tu, Wenxuan and Li, Liang and Duan, Jingcan and Chen, Cancan},
title = {Hard Sample Aware Network for Contrastive Deep Graph Clustering},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {7},
pages = {8914--8922},
doi = {10.1609/aaai.v37i7.26071}
}
EUVIMED