DeepAI AI Chat
Log In Sign Up

Benchmarking Deep Learning Interpretability in Time Series Predictions

10/26/2020
by   Aya Abdelsalam Ismail, et al.
44

Saliency methods are used extensively to highlight the importance of input features in model predictions. These methods are mostly used in vision and language tasks, and their applications to time series data is relatively unexplored. In this paper, we set out to extensively compare the performance of various saliency-based interpretability methods across diverse neural architectures, including Recurrent Neural Network, Temporal Convolutional Networks, and Transformers in a new benchmark of synthetic time series data. We propose and report multiple metrics to empirically evaluate the performance of saliency methods for detecting feature importance over time using both precision (i.e., whether identified features contain meaningful signals) and recall (i.e., the number of features with signal identified as important). Through several experiments, we show that (i) in general, network architectures and saliency methods fail to reliably and accurately identify feature importance over time in time series data, (ii) this failure is mainly due to the conflation of time and feature domains, and (iii) the quality of saliency maps can be improved substantially by using our proposed two-step temporal saliency rescaling (TSR) approach that first calculates the importance of each time step before calculating the importance of each feature at a time step.

READ FULL TEXT

page 2

page 5

page 6

page 8

page 19

page 20

page 21

page 32

11/29/2021

Improving Deep Learning Interpretability by Saliency Guided Training

Saliency methods have been widely used to highlight important input feat...
10/27/2019

Input-Cell Attention Reduces Vanishing Saliency of Recurrent Neural Networks

Recent efforts to improve the interpretability of deep neural networks u...
04/28/2020

Time Series Forecasting With Deep Learning: A Survey

Numerous deep learning architectures have been developed to accommodate ...
09/16/2019

Towards A Rigorous Evaluation Of XAI Methods On Time Series

Explainable Artificial Intelligence (XAI) methods are typically deployed...
03/15/2021

Interpretable Feature Construction for Time Series Extrinsic Regression

Supervised learning of time series data has been extensively studied for...
03/24/2020

TRACER: A Framework for Facilitating Accurate and Interpretable Analytics for High Stakes Applications

In high stakes applications such as healthcare and finance analytics, th...
01/07/2022

Churn prediction in online gambling

In business retention, churn prevention has always been a major concern....