In Multi-View Multi-Label Learning, each instance is described by several heterogeneous features and associated with multiple valid labels simultaneously. Existing methods mainly focus on leveraging feature-level view fusion to capture a common representation for multi-label classifier induction. In this paper, we take a new perspective and propose a new semantic-level fusion model named Common-Individual Semantic Fusion Multi-View Multi-Label Learning Method (CISF). Different from previous feature-level fusion model, our proposed method directly focuses on semantic-level view fusion and simultaneously take both the common semantic across different views and the individual semantic of each specific view into consideration. Specifically, we first assume each view involves some common semantic labels while owns a few exclusive semantic labels. Then, the common and exclusive semantic labels are separately forced to be consensus and diverse to excavate the consistences and complementarities among different views. Afterwards, we introduce the low-rank and sparse constraint to highlight the label co-occurrence relationship of common semantics and the view-specific expression of individual semantics. We provide theoretical guarantee for the strict convexity of our method by properly setting parameters. Extensive experiments on various data sets have verified the superiority of our method.
11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
When dealing with multi-view data, the heterogeneity of data attributes across different views often leads to label ambiguity. To effectively address this challenge, this paper designs a Multi-View Partial-Label Learning (MVPLL) framework, where each training instance is described by multiple view features and associated with a set of candidate labels, among which only one is correct. The key to deal with such problem lies in how to effectively fuse multi-view information and accurately disambiguate these ambiguous labels. In this paper, we propose a novel approach named CFDM, which explores the consistency and complementarity of multi-view data by multi-view contrastive fusion and reduces label ambiguity by multi-class contrastive prototype disambiguation. Specifically, we first extract view-specific representations using multiple view-specific autoencoders, and then integrate multi-view information through both inter-view and intra-view contrastive fusion to enhance the distinctiveness of these representations. Afterwards, we utilize these distinctive representations to establish and update prototype vectors for each class within each view. Based on these, we apply contrastive prototype disambiguation to learn global class prototypes and accordingly reduce label ambiguity. In our model, multi-view contrastive fusion and multi-class contrastive prototype disambiguation are conducted mutually to enhance each other within a coherent framework, leading to a more ideal classification performance. Experimental results on multiple datasets have demonstrated that our proposed method is superior to other state-of-the-art methods.
8 December 2022 in Security and Communication Networks
With the continuous maturity and development of the big data technology system, deep learning has been widely used in the field of the Industrial Internet of Things. However, the traditional training model with centralized data is prone to the leakage of private information in the industry, such as facial information. In recent years, federated learning solves the problem of privacy leakage caused by data sharing by not sharing data and only contributing to local models. Federated learning does not share data, which also makes it impossible to evaluate the contribution of each client to the federated task. We propose a federated learning framework based on data value evaluation. In this method, under the premise of effectively completing the training task of federated learning and ensuring the privacy of client data, a data value evaluator is designed in the central server, and the model uploaded by the client is evaluated to obtain the corresponding selection probability as the model aggregation weight. Experimental results show that the proposed method improves the accuracy of the global model obtained by existing federated aggregation.
9 December 2021 in Concurrency and Computation: Practice and Experience