2022-10-05 更新
Interpretable Representations in Explainable AI: From Theory to Practice
Authors:Kacper Sokol, Peter Flach
Interpretable representations are the backbone of many explainers designed for black-box predictive systems based on artificial intelligence and machine learning algorithms. They translate the low-level data representation necessary for good predictive performance into high-level human-intelligible concepts used to convey the explanatory insights. Notably, the explanation type and its cognitive complexity are directly controlled by the interpretable representation, allowing to target a particular audience and use case. However, many explainers built upon interpretable representations overlook their merit and fall back on default solutions that often carry implicit assumptions, thereby degrading the explanatory power and reliability of such techniques. To address this problem, we study properties of interpretable representations that encode presence and absence of human-comprehensible concepts. We show how they are operationalised for tabular, image and text data; discuss their assumptions, strengths and weaknesses; identify their core building blocks; and scrutinise their parameterisation. In particular, this in-depth analysis allows us to pinpoint their explanatory properties, desiderata and scope for (malicious) manipulation in the context of tabular data, where a linear model is used to quantify the influence of interpretable concepts on a black-box prediction. Our findings support a range of recommendations for designing trustworthy interpretable representations; specifically, the benefits of class-aware (supervised) discretisation of tabular data, e.g., with decision trees, and sensitivity of image interpretable representations to segmentation granularity and occlusion colour.
PDF
点此查看论文截图
Evaluation of importance estimators in deep learning classifiers for Computed Tomography
Authors:Lennart Brocki, Wistan Marchadour, Jonas Maison, Bogdan Badic, Panagiotis Papadimitroulas, Mathieu Hatt, Franck Vermet, Neo Christopher Chung
Deep learning has shown superb performance in detecting objects and classifying images, ensuring a great promise for analyzing medical imaging. Translating the success of deep learning to medical imaging, in which doctors need to understand the underlying process, requires the capability to interpret and explain the prediction of neural networks. Interpretability of deep neural networks often relies on estimating the importance of input features (e.g., pixels) with respect to the outcome (e.g., class probability). However, a number of importance estimators (also known as saliency maps) have been developed and it is unclear which ones are more relevant for medical imaging applications. In the present work, we investigated the performance of several importance estimators in explaining the classification of computed tomography (CT) images by a convolutional deep network, using three distinct evaluation metrics. First, the model-centric fidelity measures a decrease in the model accuracy when certain inputs are perturbed. Second, concordance between importance scores and the expert-defined segmentation masks is measured on a pixel level by a receiver operating characteristic (ROC) curves. Third, we measure a region-wise overlap between a XRAI-based map and the segmentation mask by Dice Similarity Coefficients (DSC). Overall, two versions of SmoothGrad topped the fidelity and ROC rankings, whereas both Integrated Gradients and SmoothGrad excelled in DSC evaluation. Interestingly, there was a critical discrepancy between model-centric (fidelity) and human-centric (ROC and DSC) evaluation. Expert expectation and intuition embedded in segmentation maps does not necessarily align with how the model arrived at its prediction. Understanding this difference in interpretability would help harnessing the power of deep learning in medicine.
PDF 4th International Workshop on EXplainable and TRAnsparent AI and Multi-Agent Systems (EXTRAAMAS 2022) - International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS)
点此查看论文截图
2022-10-05 更新
Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction
Authors:Yikai Wang, Fuchun Sun, Wenbing Huang, Fengxiang He, Dacheng Tao
Multimodal fusion and multitask learning are two vital topics in machine learning. Despite the fruitful progress, existing methods for both problems are still brittle to the same challenge — it remains dilemmatic to integrate the common information across modalities (resp. tasks) meanwhile preserving the specific patterns of each modality (resp. task). Besides, while they are actually closely related to each other, multimodal fusion and multitask learning are rarely explored within the same methodological framework before. In this paper, we propose Channel-Exchanging-Network (CEN) which is self-adaptive, parameter-free, and more importantly, applicable for multimodal and multitask dense image prediction. At its core, CEN adaptively exchanges channels between subnetworks of different modalities. Specifically, the channel exchanging process is self-guided by individual channel importance that is measured by the magnitude of Batch-Normalization (BN) scaling factor during training. For the application of dense image prediction, the validity of CEN is tested by four different scenarios: multimodal fusion, cycle multimodal fusion, multitask learning, and multimodal multitask learning. Extensive experiments on semantic segmentation via RGB-D data and image translation through multi-domain input verify the effectiveness of CEN compared to state-of-the-art methods. Detailed ablation studies have also been carried out, which demonstrate the advantage of each component we propose. Our code is available at https://github.com/yikaiw/CEN.
PDF Accepted by TPAMI 2022. Code is available at https://github.com/yikaiw/CEN. arXiv admin note: text overlap with arXiv:2011.05005
点此查看论文截图