Abstract
Explanation for deep learning models on time series classification (TSC) tasks is an important and challenging problem. Most existing approaches use attribution maps to explain outcomes. However, they have limitations in generating explanations that are well-aligned with humans’s perceptions. Recently, LIME-based approaches provide a more meaningful explanation via segmenting the data. However, these approaches are still suffering from shortcomings in the processes of segment generation and evaluation. In this paper, we propose a novel time series explanation approach called InteDisUX to overcome these problems. Our technique utilizes the segment-level integrated gradient (SIG) for calculating importance scores for an initial set of small and equal segments before iteratively merge two consecutive ones to create better explanations under a unique greedy strategy guided by two new proposed metrics including discrimination and faithfulness gains. By this way, our method does not depend on predefined segments like others while being robusts to instability, poor local fidelity and data imbalance like LIMEbased methods. Furthermore, InteDisUX is the first work to use the model’s information to improve the set of segments for time series explanation. Extensive experiments show that our method outperforms LIME-based ones in 12 datasets in terms of faithfulness and 8/12 datasets in terms of robustness.
Original language | English |
---|---|
Title of host publication | 39th AAAI Conference on Artificial Intelligence: Proceedings |
Publisher | AAAI Press |
Number of pages | 8 |
Publication status | Accepted - 11 Dec 2024 |
Event | 39th Annual AAAI Conference on Artificial Intelligence 2025 - Philadelphia, United States Duration: 25 Feb 2025 → 04 Mar 2025 Conference number: 39 https://aaai.org/conference/aaai/aaai-25/ |
Publication series
Name | Proceedings of the AAAI Conference on Artificial Intelligence |
---|---|
Publisher | AAAI Press |
ISSN (Print) | 2159-5399 |
ISSN (Electronic) | 2374-3468 |
Conference
Conference | 39th Annual AAAI Conference on Artificial Intelligence 2025 |
---|---|
Abbreviated title | AAAI-25 |
Country/Territory | United States |
City | Philadelphia |
Period | 25/02/2025 → 04/03/2025 |
Internet address |
Keywords
- InteDisUX
- discriminative user-centric
- time series