Interpretable machine learning: Fundamental principles and 10 grand challenges

C Rudin, C Chen, Z Chen, H Huang… - Statistic …, 2022 - projecteuclid.org
Interpretability in machine learning (ML) is crucial for high stakes decisions and
troubleshooting. In this work, we provide fundamental principles for interpretable ML, and …

Explainable ai for text classification: Lessons from a comprehensive evaluation of post hoc methods

M Cesarini, L Malandri, F Pallucchini, A Seveso… - Cognitive …, 2024 - Springer
This paper addresses the notable gap in evaluating eXplainable Artificial Intelligence (XAI)
methods for text classification. While existing frameworks focus on assessing XAI in areas …

Market-aware Long-term Job Skill Recommendation with Explainable Deep Reinforcement Learning

Y Sun, Y Ji, H Zhu, F Zhuang, Q He… - ACM Transactions on …, 2024 - dl.acm.org
Continuously learning new skills is essential for talents to gain a competitive advantage in
the labor market. Despite extensive efforts on relevance-or preference-based skill …

A Comprehensive Survey on Self-Interpretable Neural Networks

Y Ji, Y Sun, Y Zhang, Z Wang, Y Zhuang… - ar**
R Ragodos, T Wang, Q Lin… - Advances in Neural …, 2022 - proceedings.neurips.cc
While deep reinforcement learning has proven to be successful in solving control tasks,
the``black-box''nature of an agent has received increasing concerns. We propose a …

Prediction with Visual Evidence: Sketch Classification Explanation via Stroke-Level Attributions

S Liu, J Li, H Zhang, L Xu, X Cao - IEEE Transactions on Image …, 2023 - ieeexplore.ieee.org
Sketch classification models have been extensively investigated by designing a task-driven
deep neural network. Despite their successful performances, few works have attempted to …

Prominet: Prototype-based multi-view network for interpretable email response prediction

Y Wang, P Vijayaraghavan, E Degan - arxiv preprint arxiv:2310.16753, 2023 - arxiv.org
Email is a widely used tool for business communication, and email marketing has emerged
as a cost-effective strategy for enterprises. While previous studies have examined factors …

Prototype Learning for Medical Time Series Classification via Human–Machine Collaboration

J **e, Z Wang, Z Yu, Y Ding, B Guo - Sensors, 2024 - mdpi.com
Deep neural networks must address the dual challenge of delivering high-accuracy
predictions and providing user-friendly explanations. While deep models are widely used in …

Adaax: Explaining recurrent neural networks by learning automata with adaptive states

D Hong, AM Segre, T Wang - Proceedings of the 28th ACM SIGKDD …, 2022 - dl.acm.org
Recurrent neural networks (RNN) are widely used for handling sequence data. However,
their black-box nature makes it difficult for users to interpret the decision-making process …

GAProtoNet: A Multi-head Graph Attention-based Prototypical Network for Interpretable Text Classification

X Wen, W Tan, RO Weber - arxiv preprint arxiv:2409.13312, 2024 - arxiv.org
Pretrained transformer-based Language Models (LMs) are well-known for their ability to
achieve significant improvement on text classification tasks with their powerful word …