Most Multi-view Clustering approaches assume that all views are available for clustering. However, this assumption is often unrealistic as views are incrementally accumulated over time, leading to a need for continual multi-view clustering (CMVC) methods. Current approaches to CMVC leverage late fusion-based approaches, where a new model is typically learned individually for each view to obtain the corresponding partition matrix, and then used to update a consensus matrix via a moving average. These approaches are prone to view-specific noise and struggle to adapt to large gaps between different views. To address these shortcomings, we reconsider CMVC from the perspective of domain adaptation and propose AdaptCMVC, which learns how to incrementally accumulate knowledge of new views as they become available and prevents catastrophic forgetting. Specifically, a self-training framework is introduced to extend the model to new views, particularly designed to be robust to view-specific noise. Further, to combat catastrophic forgetting, a structure alignment mechanism is proposed to enable the model to explore the global group structure across multiple views. Experiments on several multi-view benchmarks demonstrate the effectiveness of our proposed method on the CMVC task. The code is available at: AdaptCMVC.

Deep Multi-view Graph Clustering (DMGC) aims to partition instances into different groups using the graph information extracted from multi-view data. The mainstream framework of DMGC methods applies graph neural networks to embed structure information into the view-specific representations and fuse them for the consensus representation. However, on one hand, we find that the graph learned in advance is not ideal for clustering as it is constructed by original multi-view data and localized connecting. On the other hand, most existing methods learn the consensus representation in a late fusion manner, which fails to propagate the structure relations across multiple views. Inspired by the observations, we propose a Structure-adaptive Unified gRaph nEural network for multi-view clusteRing (SURER), which can jointly learn a heterogeneous multi-view unified graph and robust graph neural networks for multi-view clustering. Specifically, we first design a graph structure learning module to refine the original view-specific attribute graphs, which removes false edges and discovers the potential connection. According to the view-specific refined attribute graphs, we integrate them into a unified heterogeneous graph by linking the representations of the same sample from different views. Furthermore, we use the unified heterogeneous graph as the input of the graph neural network to learn the consensus representation for each instance, effectively integrating complementary information from various views. Extensive experiments on diverse datasets demonstrate the superior effectiveness of our method compared to other state-of-the-art approaches.

Multi-view subspace clustering (MVSC), which leverages comprehensive information from multiple views to effectively reveal the intrinsic relationships among instances, has garnered significant research interest. However, previous MVSC research focuses on exploring the cross-view consistent information only in the instance representation hierarchy or affinity relationship hierarchy, which prevents a joint investigation of the multi-view consistency in multiple hierarchies. To this end, we propose a Triple-gRanularity contrastive learning framework for deep mUlti-view Subspace clusTering (TRUST), which benefits from the comprehensive discovery of valuable information from three hierarchies, including the instance, specific-affinity relationship, and consensus-affinity relationship. Specifically, we first use multiple view-specific autoencoders to extract noise-robust instance representations, which are then respectively input into the MLP model and self-representation model to obtain high-level instance representations and view-specific affinity matrices. Then, the instance and specific-affinity relationship contrastive regularization terms are separately imposed on the high-level instance representations and view specific-affinity matrices, ensuring the cross-view consistency can be found from the instance representations to the view-specific affinity matrices. Furthermore, multiple view-specific affinity matrices are fused into a consensus one associated with the consensus-affinity relationship contrastive constraint, which embeds the local structural relationship of high-level instance representations into the consensus affinity matrix. Extensive experiments on various datasets demonstrate that our method is more effective when compared with other state-of-art methods.

Graph convolutional networks (GCN), aiming to learn meaningful representations for graph data, has been popularly used in recommender systems since user-item interactions can be represented by a bipartite graph. However, GCN often suffers from the over-smoothing issue when it goes deeper, which implies that long paths between users and items are not very useful to embedding learning in recommender systems. To deal with long paths, introducing user and item links is a promising way to shorten the average path between users and items. However, due to introducing the user and item linkages, the bipartite graph becomes a heterogeneous graph. To this end, we propose a multi-aspect heterogeneous GCN model, which is to power GCN towards recommendation tasks by introducing user-user and item-item links to build the heterogeneous user- item graph. Then, we decompose it into three subgraphs and keep the global heterogeneous graph to preserve the original structure information. Specifically, we apply GCN to learn user and item representations from both the subgraphs and the global graph. After that, we have multi-aspect attention to integrate the representations from GCN to obtain the final user and item representation. Extensive experiments on three real-world datasets show that the proposed approaches achieve significant improvements over state-of-the-art methods.

Variational autoencoder (VAE) is considered as an emerging model for ensuring competitive performance in recom-mender systems. However, its performance is severely limited by the amount of training examples and, as a result, existing VAE models may fail to provide satisfactory recommendation results in presence of highly sparse user-item interactions. In this paper, we propose a self-supervised VAE model, SSVAE in short, to improve the generalization ability of VAE model on the sparse interaction datasets. Concretely, we first build multiple views for each user by data augmentation, and then design a pretext task to align the representations learned from different views of each user. Particularly, SSVAE aims to optimize a combined objective of recommendation task and pretext task, making them to rein-force each other during the learning process. Our encouraging experimental results on three real-world benchmarks validate the superiority of our SSVAE model to state-of-the-art VAE style recommendation techniques.