TY - GEN

T1 - IndMask

T2 - 27th European Conference on Artificial Intelligence, ECAI 2024

AU - Nasr, Seham

AU - Sikdar, Sandipan

N1 - Publisher Copyright: © 2024 The Authors.

PY - 2024/10

Y1 - 2024/10

N2 - In this paper, we introduce IndMask, a framework for explaining decisions of black-box time series models. While there exists a plethora of methods for providing explanations of machine learning models, time series data requires additional considerations. One needs to consider the time aspect in the explanations as well as deal with a large number of input features. Recent work has proposed explaining a time series prediction by generating a mask over the input time series. Each entry in the mask corresponds to an importance score for each feature at each time step. However, these methods only generate instancewise explanations, which means a mask needs to be computed for each input individually, thereby making them unsuited for inductive settings, where explanations need to be generated for numerous inputs, and instancewise explanation generation is severely prohibitive. Additionally, these methods have mostly been evaluated on simple recurrent neural networks and are often only applicable to a specific downstream task. Our proposed framework IndMask addresses these issues by utilizing a parameterized model for mask generation. We also go beyond recurrent neural networks and deploy IndMask to transformer architectures, thereby genuinely demonstrating its model-agnostic nature. The effectiveness of IndMask is further demonstrated through experiments over real-world datasets and time series classification and forecasting tasks. It is also computationally efficient and can be deployed in conjunction with any time series model.

AB - In this paper, we introduce IndMask, a framework for explaining decisions of black-box time series models. While there exists a plethora of methods for providing explanations of machine learning models, time series data requires additional considerations. One needs to consider the time aspect in the explanations as well as deal with a large number of input features. Recent work has proposed explaining a time series prediction by generating a mask over the input time series. Each entry in the mask corresponds to an importance score for each feature at each time step. However, these methods only generate instancewise explanations, which means a mask needs to be computed for each input individually, thereby making them unsuited for inductive settings, where explanations need to be generated for numerous inputs, and instancewise explanation generation is severely prohibitive. Additionally, these methods have mostly been evaluated on simple recurrent neural networks and are often only applicable to a specific downstream task. Our proposed framework IndMask addresses these issues by utilizing a parameterized model for mask generation. We also go beyond recurrent neural networks and deploy IndMask to transformer architectures, thereby genuinely demonstrating its model-agnostic nature. The effectiveness of IndMask is further demonstrated through experiments over real-world datasets and time series classification and forecasting tasks. It is also computationally efficient and can be deployed in conjunction with any time series model.

UR - http://www.scopus.com/inward/record.url?scp=85213333783&partnerID=8YFLogxK

U2 - 10.3233/FAIA240603

DO - 10.3233/FAIA240603

M3 - Conference contribution

AN - SCOPUS:85213333783

T3 - Frontiers in Artificial Intelligence and Applications

SP - 1108

EP - 1115

BT - ECAI 2024 - 27th European Conference on Artificial Intelligence, Including 13th Conference on Prestigious Applications of Intelligent Systems, PAIS 2024, Proceedings

A2 - Endriss, Ulle

A2 - Melo, Francisco S.

A2 - Bach, Kerstin

A2 - Bugarin-Diz, Alberto

A2 - Alonso-Moral, Jose M.

A2 - Barro, Senen

A2 - Heintz, Fredrik

Y2 - 19 October 2024 through 24 October 2024

ER -