The conversational recommendation system (CRS) breaks the limitations of traditional static methods, presenting a novel framework for personalized recommendations with real-time adaptability and dynamic interactions. Existing methods predominantly focus on the balance between ”exploration and exploitation (E&E)”, but t...
Di Jin, Run-Ze Li, Jia-Qi Cui et al.· ACM Transactions on Informat...· 0 citations
This work proposes a novel Granular Envelope Contrastive Learning (GECL) method that explicitly models intra-class variations by generating multiple granular envelopes for each class, and jointly reduces domain discrepancy and enhances feature discriminability.
Pufei Li, Pin Wang, Yongming Li et al.· Neural Networks· 0 citations
Anomaly detection (AD) has attracted increasing attention because of its importance in identifying unusual patterns across widely applications. Existing reconstruction-based AD methods have shown strong capability in modeling complex data distributions, but still face several limitations. First, most methods assume tha...
Jiao-Long Chen, Ye Liu, Yuhua Qian et al.· IEEE Transactions on Cyberne...· 0 citations
Information granularity provides a framework for machine intelligence to simulate human cognitive processes in problem-solving, enabling machines to make more flexible and adaptive decisions in complex data environments. However, most existing information granularities are based on fuzzy c-mean (FCM) or K-means cluster...
Wentao Li, Xuan-Zhen Zhao, W. Pedrycz et al.· IEEE Transactions on Cyberne...· 0 citations
In this study, we propose an incrementally expanding fuzzy neural module network (FNMN) designed to effectively handle both low- and high-dimensional problems without relying on dimensionality reduction techniques. The proposed framework adopts a modular and hierarchical architecture, in which univariate fuzzy neural m...
Eun-Hu Kim, Hao Huang, Zheng Wang et al.· IEEE Transactions on Cyberne...· 0 citations
Intrinsic Logit-Based Debiasing (ILBD), a robust post-hoc framework that estimates bias directly from task-relevant data without external dependencies and class priors, and effectively rectifies the classifier's bias directly from the inherent statistical patterns of the training data.
