The Accuracy Paradox: Empirical Diagnostic of Default Decision Thresholds in Multi-Label Enzyme Commission Prediction [With Code]
研究解决了酶委员会编号预测中默认决策阈值导致的准确性悖论问题，通过系统诊断和特定目标阈值优化方法来提高预测准确性。
0 citationsRead paper
Selected work
Representative Papers
WIDE: Wildcard Inference with Dynamic Expansion for Cross-Modal Generative Retrieval
本文针对跨模态生成检索中的信息不对称问题，提出WIDE方法，通过动态扩展搜索空间和重新排序来减少强制性幻觉，提高检索准确性。
0 citationsRead paper
ReBridge-Flow: Re-Coupling Posterior Bridges in Flow Matching for Image Restoration
为解决图像恢复中测量约束导致的源-清洁端点耦合破坏问题，提出ReBridge-Flow方法，通过重新耦合后验桥并引入后验桥缺陷来改进局部桥兼容性和恢复图像的一致性。
0 citationsRead paper
Modality Disentangled Learning for Incomplete Multimodal Emotion Recognition: A Primitive Memory Distillation Perspective
为解决多模态情感识别中模态缺失问题，提出Primitive Memory Distillation框架，通过解耦和记忆库方法提高表示稳定性和鲁棒性。
0 citationsRead paper
EGRL: Edge generation-guided relation-aware learning for RNA-protein interaction prediction
This work addresses the limitations of existing graph neural network–based methods for RNA–protein interaction prediction, which rely on predefined meta-paths or homogeneous graphs and thus exhibit poor generalization under data sparsity and cold-start scenarios. To overcome these challenges, the authors propose EGRL, a novel framework that implicitly learns meta-paths to automatically capture semantic relationships in heterogeneous graphs. EGRL integrates a multi-relational attention mechanism with a learnable soft edge generator, enabling effective modeling of cold-start nodes. The framework jointly optimizes the primary interaction prediction task alongside an auxiliary graph structure generation task. Extensive experiments on four benchmark datasets demonstrate that EGRL significantly outperforms current state-of-the-art methods, achieving an AUROC of 0.867 and an AUPR of 0.861 in cold-start settings—improvements of 8.6% and 5.0%, respectively.
0 citationsRead paper
Recent publications
Latest Papers
The Accuracy Paradox: Empirical Diagnostic of Default Decision Thresholds in Multi-Label Enzyme Commission Prediction [With Code]
研究解决了酶委员会编号预测中默认决策阈值导致的准确性悖论问题，通过系统诊断和特定目标阈值优化方法来提高预测准确性。
0 citationsRead paper
WIDE: Wildcard Inference with Dynamic Expansion for Cross-Modal Generative Retrieval
本文针对跨模态生成检索中的信息不对称问题，提出WIDE方法，通过动态扩展搜索空间和重新排序来减少强制性幻觉，提高检索准确性。
0 citationsRead paper
ReBridge-Flow: Re-Coupling Posterior Bridges in Flow Matching for Image Restoration
为解决图像恢复中测量约束导致的源-清洁端点耦合破坏问题，提出ReBridge-Flow方法，通过重新耦合后验桥并引入后验桥缺陷来改进局部桥兼容性和恢复图像的一致性。
0 citationsRead paper
Modality Disentangled Learning for Incomplete Multimodal Emotion Recognition: A Primitive Memory Distillation Perspective
为解决多模态情感识别中模态缺失问题，提出Primitive Memory Distillation框架，通过解耦和记忆库方法提高表示稳定性和鲁棒性。
0 citationsRead paper
EGRL: Edge generation-guided relation-aware learning for RNA-protein interaction prediction
This work addresses the limitations of existing graph neural network–based methods for RNA–protein interaction prediction, which rely on predefined meta-paths or homogeneous graphs and thus exhibit poor generalization under data sparsity and cold-start scenarios. To overcome these challenges, the authors propose EGRL, a novel framework that implicitly learns meta-paths to automatically capture semantic relationships in heterogeneous graphs. EGRL integrates a multi-relational attention mechanism with a learnable soft edge generator, enabling effective modeling of cold-start nodes. The framework jointly optimizes the primary interaction prediction task alongside an auxiliary graph structure generation task. Extensive experiments on four benchmark datasets demonstrate that EGRL significantly outperforms current state-of-the-art methods, achieving an AUROC of 0.867 and an AUPR of 0.861 in cold-start settings—improvements of 8.6% and 5.0%, respectively.
0 citationsRead paper