TCNL: Transparent and Controllable Network Learning Via Embedding Human-Guided Concepts

TL;DR

TCNL introduces a human-guided, concept-based approach to enhance transparency and controllability in CNN models, enabling better understanding and manipulation of learned features for specific tasks.

Contribution

The paper proposes a novel concept-based method, TCNL, integrating human-defined concepts into CNNs to improve interpretability and control over the model's learned representations.

Findings

Improved transparency-interpretability through concept encoding.

Enhanced controllability of CNNs with human-guided concepts.

Generalizable approach applicable to various classification tasks.

Abstract

Explaining deep learning models is of vital importance for understanding artificial intelligence systems, improving safety, and evaluating fairness. To better understand and control the CNN model, many methods for transparency-interpretability have been proposed. However, most of these works are less intuitive for human understanding and have insufficient human control over the CNN model. We propose a novel method, Transparent and Controllable Network Learning (TCNL), to overcome such challenges. Towards the goal of improving transparency-interpretability, in TCNL, we define some concepts for specific classification tasks through scientific human-intuition study and incorporate concept information into the CNN model. In TCNL, the shallow feature extractor gets preliminary features first. Then several concept feature extractors are built right after the shallow feature extractor to learn high-dimensional concept representations. The concept feature extractor is encouraged to encode information related to the predefined concepts. We also build the concept mapper to visualize features extracted by the concept extractor in a human-intuitive way. TCNL provides a generalizable approach to transparency-interpretability. Researchers can define concepts corresponding to certain classification tasks and encourage the model to encode specific concept information, which to a certain extent improves transparency-interpretability and the controllability of the CNN model. The datasets (with concept sets) for our experiments will also be released (https://github.com/bupt-ai-cz/TCNL).