The paper "Reliable Conflicting Multi-View Learning" addresses the challenge of handling conflicting multi-view data, where different views may provide conflicting information. Traditional methods often assume strict alignment of multiple views, but real-world data often contains low-quality conflicting instances. The authors propose a new problem, Reliable Conflicting Multi-View Learning (RCML), which requires models to provide decision results and attached reliabilities for conflicting multi-view data. To solve this, they develop an Evidential Conflicting Multi-View Learning (ECML) method. ECML first learns view-specific evidence using Deep Neural Networks (DNNs) and then constructs view-specific opinions consisting of decision results and reliability. In the multi-view fusion stage, a conflictive opinion aggregation strategy is proposed, which theoretically models the relation between multi-view common and view-specific reliabilities. Experiments on six datasets demonstrate the effectiveness of ECML in terms of accuracy, reliability, and robustness compared to state-of-the-art methods. The code for ECML is available at https://github.com/jiajuns/RCML.The paper "Reliable Conflicting Multi-View Learning" addresses the challenge of handling conflicting multi-view data, where different views may provide conflicting information. Traditional methods often assume strict alignment of multiple views, but real-world data often contains low-quality conflicting instances. The authors propose a new problem, Reliable Conflicting Multi-View Learning (RCML), which requires models to provide decision results and attached reliabilities for conflicting multi-view data. To solve this, they develop an Evidential Conflicting Multi-View Learning (ECML) method. ECML first learns view-specific evidence using Deep Neural Networks (DNNs) and then constructs view-specific opinions consisting of decision results and reliability. In the multi-view fusion stage, a conflictive opinion aggregation strategy is proposed, which theoretically models the relation between multi-view common and view-specific reliabilities. Experiments on six datasets demonstrate the effectiveness of ECML in terms of accuracy, reliability, and robustness compared to state-of-the-art methods. The code for ECML is available at https://github.com/jiajuns/RCML.