Harnessing the Power of Explanations for Incremental Training: A LIME-Based Approach
원문 초록
Explainability of neural network prediction is essential to understand feature importance and gain interpretable insight into neural network performance. However, explanations of neural network outcomes are mostly limited to visualization, and there is scarce work that looks to use these explanations as feedback to improve model performance. In this work, model explanations are fed back to the feed-forward training to help the model generalize better. To this extent, a custom weighted loss where the weights are generated by considering the Euclidean distances between true LIME (Local Interpretable Model-Agnostic Explanations) explanations and model-predicted LIME explanations is proposed. Also, in practical training scenarios, developing a solution that can help the model learn sequentially without losing information on previous data distribution is imperative due to the unavailability of all the training data at once. Thus, the framework incorporates the custom weighted loss with Elastic Weight Consolidation (EWC) to maintain performance in sequential testing sets. The proposed custom training procedure results in a consistent enhancement of accuracy ranging from 0.5% to 1.5% throughout all phases of the incremental learning setup compared to traditional loss-based training methods for the keyword spotting task using the Google Speech Commands dataset.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spotting
Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts
Enhancing interpretability of rule-based classifiers through feature graphs
Advances in Small-Footprint Keyword Spotting: A Comprehensive Review of Efficient Models and Algorithms
GLAP: General contrastive audio-text pretraining across domains and languages
Profiling Electric Vehicles via Early Charging Voltage Patterns
토론
이 논문과 연결된 포럼 글이 아직 없습니다.