GraphLearner: Graph Node Clustering with Fully Learnable Augmentation

Xihong Yang, Erxue Min, KE LIANG, Yue Liu, Siwei Wang, sihang zhou, Huijun Wu, Xinwang Liu, En Zhu

Abstract: Contrastive deep graph clustering (CDGC) leverages the power of contrastive learning to group nodes into different clusters. The quality of contrastive samples is crucial for achieving better performance, making augmentation techniques a key factor in the process. However, the augmentation samples in existing methods are always predefined by human experiences, and agnostic from the downstream task clustering, thus leading to high human resource costs and poor performance. To overcome these limitations, we propose a Graph Node Clustering with Fully Learnable Augmentation, termed GraphLearner. It introduces learnable augmentors to generate high-quality and task-specific augmented samples for CDGC. GraphLearner incorporates two learnable augmentors specifically designed for capturing attribute and structural information. Moreover, we introduce two refinement matrices, including the high-confidence pseudo-label matrix and the cross-view sample similarity matrix, to enhance the reliability of the learned affinity matrix. During the training procedure, we notice the distinct optimization goals for training learnable augmentors and contrastive learning networks. In other words, we should both guarantee the consistency of the embeddings as well as the diversity of the augmented samples. To address this challenge, we propose an adversarial learning mechanism within our method. Besides, we leverage a two-stage training strategy to refine the high-confidence matrices. Extensive experimental results on six benchmark datasets validate the effectiveness of GraphLearner.

Primary Subject Area: [Content] Multimodal Fusion

Secondary Subject Area: [Experience] Multimedia Applications

Relevance To Conference: This paper is highly relevant to ACM MM and proposes a graph method that can be applied in the multimedia field. There were also many graph related works in the previous ACM MM, e.g., graph-based recommendation, graph-based multi-view learning, graph representation learning.

Submission Number: 1202