8 papers
Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaboration
Yilin Zhang, Han Jiang, Cai Xu +2
Heterogeneous model collaboration seeks to exploit the complementary strengths of different models to balance predictive performance and inference cost. Existing approaches typical…
Are Independently Estimated View Uncertainties Comparable? Unified Routing for Trusted Multi-View Classification
Yilin Zhang, Cai Xu, Haishun Chen +2
Trusted multi-view classification typically relies on a view-wise evidential fusion process: each view independently produces class evidence and uncertainty, and the final predicti…
AdaMuS: Adaptive Multi-view Sparsity Learning for Dimensionally Unbalanced Data
Cai Xu, Changhao Sun, Ziyu Guan +1
Multi-view learning primarily aims to fuse multiple features to describe data comprehensively. Most prior studies implicitly assume that different views share similar dimensions. I…
Differentiable Geometric Indexing for End-to-End Generative Retrieval
Xujing Wang, Yufeng Chen, Boxuan Zhang +7
Generative Retrieval (GR) has emerged as a promising paradigm to unify indexing and search within a single probabilistic framework. However, existing approaches suffer from two int…
Simple Yet Effective Selective Imputation for Incomplete Multi-view Clustering
Cai Xu, Jinlong Liu, Yilin Zhang +3
Incomplete Multi-view Clustering (IMC) has emerged as a significant challenge in multi-view learning. A predominant line for IMC is data imputation; however, indiscriminate imputat…
Target-Agnostic Calibration under Distribution Shift with Frequency-Aware Gradient Rectification
Yilin Zhang, Cai Xu, You Wu +2
Real-world model deployments inevitably encounter distribution shifts, rendering the confidence estimates of deep neural networks highly unreliable, posing severe risks in safety-c…
Fairness-Aware Multi-view Evidential Learning with Adaptive Prior
Haishun Chen, Cai Xu, Jinlong Yu +5
Multi-view evidential learning aims to integrate information from multiple views to improve prediction performance and provide trustworthy uncertainty esitimation. Most previous me…
Conf-GNNRec: Quantifying and Calibrating the Prediction Confidence for GNN-based Recommendation Methods
Meng Yan, Cai Xu, Xujing Wang +3
Recommender systems based on graph neural networks perform well in tasks such as rating and ranking. However, in real-world recommendation scenarios, noise such as user misuse and…