Integrating Intrinsic and Extrinsic Explainability: The Relevance of Understanding Neural Networks for Human-Robot Interaction

Breaking Batch Normalization for better explainability of Deep Neural Networks through Layer-wise Relevance Propagation

The lack of transparency of neural networks stays a major break for their use. The Layerwise Relevance Propagation technique builds heat-maps representing the relevance of each input in the model s decision. The relevance spreads backward from the last to the first layer of the Deep Neural Network. Layer-wise Relevance Propagation does not manage normalization layers, in this work we suggest a method to include normalization layers. Specifically, we build an equivalent network fusing normalization layers and convolutional or fully connected layers. Heatmaps obtained with our method on MNIST an…

面向更智能机器人的多模态上下文表示增强可解释性研究

Enhancing Explainability with Multimodal Context Representations for Smarter Robots

针对人机交互中机器人多模态感知推理及可解释性不足的问题，提出含多模态联合表示与时间对齐模块的通用可解释多模态上下文表示框架，可评估语音与视觉的相关性，助力提升人机交互可解释性。

通过相对绝对幅度分层相关性传播与多分量评估推进基于归因的神经网络可解释性研究

Advancing Attribution-Based Neural Network Explainability through Relative Absolute Magnitude Layer-Wise Relevance Propagation and Multi-Component Evaluation

针对现有分层相关性传播（LRP）方法及归因评估指标的不足，提出相对绝对幅度LRP新方法与融合多特性的评估指标，在ImageNet、PascalVOC数据集上验证了其在Vision Transformer上的归因解释优势。

Explainability of Traditional and Deep Learning Models on Longitudinal Healthcare Records

Recent advances in deep learning have led to interest in training deep learning models on longitudinal healthcare records to predict a range of medical events, with models demonstrating high predictive performance. Predictive performance is necessary but insufficient, however, with explanations and reasoning from models required to convince clinicians for sustained use. Rigorous evaluation of explainability is often missing, as comparisons between models (traditional versus deep) and various explainability methods have not been well-studied. Furthermore, ground truths needed to evaluate explai…

基于层次注意力的图神经网络与相关性驱动剪枝

Hierarchical Attention-based Graph Neural Network with Relevance-driven Pruning

本文提出HA-HeteroGNN框架，通过统一的可解释性到剪枝流程解决异构图中节点类型可解释性不足和计算开销大的问题，实验显示剪枝能提升分类准确率并降低计算开销。

利用可扩展的谱神经网络方法估计全局输入相关性并强制稀疏表示

Estimating Global Input Relevance and Enforcing Sparse Representations with a Scalable Spectral Neural Network Approach

本文提出了一种基于谱神经网络的方法，通过谱重参数化估计输入相关性并强制稀疏表示，提升模型可解释性。