Tutorial on Deep Learning Interpretation: A Data Perspective

Time: 2:00 PM - 5:30 PM, EST

Room: Augusta H

Oct 18th, 2022.

Atlanta, Georgia, USA


Zhou Yang

GWU

zhou_yang@gwu.edu

Fan Yang

Rice University

fy19@rice.edu

Ninghao Liu

UGA

ninghao.liu@uga.edu

Xia "Ben" Hu

Rice University

xia.hu@rice.edu

Fang Jin

George Washington University

fangjin@gwu.edu

Goal 1

Image Interpretation

Goal 2

Graph Neural Network Interpretation

Goal 3

Text Interpretation

Goal 4

Deep Reinforcement Learning Interpretation

Goal 5

Tools and Hands On Tutorial

Abstract

Deep learning models have achieved exceptional predictive performance in a wide variety of tasks, ranging from computer vision, natural language processing, to graph mining. Many businesses and organizations across diverse domains are now building large-scale applications based on deep learning. However, there are growing concerns, regarding the fairness, security, and trustworthiness of these models, largely due to the opaque nature of their decision processes. Recently, there has been an increasing interest in explainable deep learning that aims to reduce the opacity of a model by explaining its behavior, its predictions, or both, thus building trust between human and complex deep learning models. A collection of explanation methods have been proposed in recent years that address the problem of low explainability and opaqueness of models. In this tutorial, we introduce recent explanation methods from a data perspective, targeting models that process image data, text data, and graph data, respectively. We will compare their strengths and limitations, and offer real-world applications. Lastly, we will introduce hands on examples and case studies of popular interpretation tools.

Slides

CIKM_Tutorial_Oct17_2.pdf

REFERENCES

[1] Shunyan Luo, Emre Barut, and Fang Jin. Statistically Consistent Saliency Estimation, International Conference on Computer Vision, ICCV 2021.

[2] Mengnan Du, Ninghao Liu, Qingquan Song, and Xia Hu. 2018. Towards explanation of dnn-based prediction with guided feature inversion. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1358–1367.

[3] Qizhang Feng, Ninghao Liu, Fan Yang, Ruixiang Tang, Mengnan Du, and Xia Hu. 2021. DEGREE: Decomposition Based Explanation for Graph Neural Networks. In International Conference on Learning Representations.

[4] Qiaoyu Tan, Jianwei Zhang, Jiangchao Yao, Ninghao Liu, Jingren Zhou, Hongxia Yang, and Xia Hu. 2021. Sparse-interest network for sequential recommendation. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining. 598–606.

[5] Xiaotian Han, Zhimeng Jiang, Ninghao Liu, Qingquan Song, Jundong Li, and Xia Hu. 2022. Geometric Graph Representation Learning via Maximizing Rate Reduction. In Proceedings of the ACM Web Conference 2022. 1226–1237.