Interpreting Deep Models through the Lens of Data

Identification of input data points relevant for the classifier (i.e. serve as the support vector) has recently spurred the interest of researchers for both interpretability as well as dataset debugging. This paper presents an in-depth analysis of the methods which attempt to identify the influence of these data points on the resulting classifier. To quantify the quality of the influence, we curated a set of experiments where we debugged and pruned the dataset based on the influence information obtained from different methods. To do so, we provided the classifier with mislabeled examples that hampered the overall performance. Since the classifier is a combination of both the data and the model, therefore, it is essential to also analyze these influences for the interpretability of deep learning models. Analysis of the results shows that some interpretability methods can detect mislabels better than using a random approach, however, contrary to the claim of these methods, the sample selection based on the training loss showed a superior performance.

[1]  Richard Nock,et al.  Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Bob L. Sturm.  An analysis of the GTZAN music genre dataset , 2012, MIRUM '12.

[3]  Seunghoon Hong,et al.  Learning Deconvolution Network for Semantic Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[4]  Pradeep Ravikumar,et al.  Representer Point Selection for Explaining Deep Neural Networks , 2018, NeurIPS.

[5]  Xiaoli Li,et al.  Deep Convolutional Neural Networks on Multichannel Time Series for Human Activity Recognition , 2015, IJCAI.

[6]  Xiang Zhang,et al.  Character-level Convolutional Networks for Text Classification , 2015, NIPS.

[7]  Tinghuai Ma,et al.  Detecting potential labeling errors for bioinformatics by multiple voting , 2014, Knowl. Based Syst..

[8]  Amaury Lendasse,et al.  MD-ELM: Originally Mislabeled Samples Detection using OP-ELM Model , 2015, Neurocomputing.

[9]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition , 2012 .

[10]  Andreas Dengel,et al.  TSViz: Demystification of Deep Learning Models for Time-Series Analysis , 2018, IEEE Access.

[11]  Percy Liang,et al.  Understanding Black-box Predictions via Influence Functions , 2017, ICML.

[12]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Xindong Wu,et al.  Eliminating Class Noise in Large Datasets , 2003, ICML.

[14]  M. Verleysen,et al.  Classification in the Presence of Label Noise: A Survey , 2014, IEEE Transactions on Neural Networks and Learning Systems.