25 September 2024 in Information Processing & Management
7 February 2024 in IEEE Transactions on Computational Social Systems
Diversified recommendation systems have gained increasing popularity in recent years. Nowadays, the emerged graph neural networks (GNNs) have been used to improve the diversity performance. Although some progresses have been made, existing works purely focus on the user–item interactions and overlook the category information, which limits the capability to capture complex diversification among users or items and leads to poor performance. In this article, our target is to integrate full category information into user and item embeddings. To this end, we propose a diversified GNN-based recommendation systems diversified graph recommendation with contrastive learning (DCL). Specifically, we design three key components in our model: 1) the user–item interaction with category-related sampling enhances the interaction of unpopular items; 2) contrastive learning between users and categories shortens the distance of representations between users and their uninteracted categories; and 3) contrastive learning between items and categories diverges the distance of representations between items and their corresponding categories. By applying these three modules, we build a multitask training framework to achieve a balance between accuracy and diversity. Experiments on real-world datasets show that our proposed DCL achieves optimal diversity while paying a little price for accuracy.
9 August 2023 in IEEE Transactions on Network Science and Engineering
Nowadays, crowdsourcing has become an increasingly popular paradigm in real-world applications. It provides a fundamental mechanism for inviting thoughts and perspectives from a wide swath of people. One of the critical issues in crowdsourcing lies in worker recruitment. However, the existing literature mainly focuses on maximizing the relevance between workers and tasks, ignoring the diversity among workers. Such neglect may lead to poor quality of task completion. In this article, we present an online worker recruitment mechanism with relevance and diversity. To comprehensively evaluate the capability of a worker group, we propose an enhanced metric called utility . We also consider a practically motivated setting in which the observed side-information of workers is insufficient due to privacy concerns. Then, we utilize contextual combinatorial multi-armed bandit to model the online worker selection process, and propose a novel D iversified H idden U pper C onfidence B ound (DH-UCB) algorithm to address the problem. Most importantly, we rigorously prove that our DH-UCB algorithm achieves significant sublinear upper regret bound with high probability. In other words, it can effectively recruit workers under insufficient information while maintaining sustainable relevance and diversity. Extensive experiments on both synthetic and large-scale real-world datasets empirically validate the advantages of our proposed mechanism.
18 May 2026 in ACM Transactions on Intelligent Systems and Technology
In recent years, social recommendation systems have emerged as a pivotal technology for enhancing recommendation accuracy by leveraging user social homophily and influence. Although many works have been devoted to this area, existing works still struggle to extract the beneficial structural information from social relationships that is beneficial for recommendations and neglect the inherent popularity bias in the social networks, which leads to suboptimal recommendation performances. To address these challenges, we propose a novel framework termed Causal Disentanglement-Enhanced Diffusion Denoising for Social Recommendation (CaDDiSR). This framework first employs causal graphs to disentangle the complexities of social relationships, generating user representations with high-order structures, which are subsequently used as inputs to a diffusion process to effectively denoise social networks and retain social signals beneficial for recommendation tasks. Furthermore, the framework integrates a bidirectional knowledge distillation mechanism, which balances user representations between social and recommendation contexts, thereby facilitating the effective fusion of their respective advantages while simultaneously mitigating noise interference and enhancing overall system performance. Finally, cross-domain contrastive learning is utilized to optimize user and item representations, ensuring consistency in recommendation performance across diverse scenarios. Experimental results on multiple real-world datasets demonstrate that CaDDiSR significantly outperforms existing baseline models, substantiating its superior performance.