Incorporating Priors with Feature Attribution on Text Classification

2019/06/19 by Frederick Liu, Liu, Frederick, Besim Avci +1 · 1 citation
Computer Science · #Computation and Language (cs.CL) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning and Data Classification #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1906.08286

openalex publication_date 2019/06/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Feature attribution methods, proposed recently, help users interpret the predictions of complex models. Our approach integrates feature attributions into the objective function to allow machine learning practitioners to incorporate priors in model building. To demonstrate the effectiveness our technique, we apply it to two tasks: (1) mitigating unintended bias in text classifiers by neutralizing identity terms; (2) improving classifier performance in a scarce data setting by forcing the model to focus on toxic terms. Our approach adds an L2 distance loss between feature attributions and task-specific prior values to the objective. Our experiments show that i) a classifier trained with our technique reduces undesired model biases without a trade off on the original task; ii) incorporating priors helps model performance in scarce data settings.

Citations

• Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word\n Embeddings
• European Union Regulations on Algorithmic Decision Making and a “Right to Explanation”
• Equality of Opportunity in Supervised Learning
• Axiomatic Attribution for Deep Networks
• Understanding Black-box Predictions via Influence Functions
• SmoothGrad: removing noise by adding noise
• Distilling a Neural Network Into a Soft Decision Tree
• Consistent Individualized Feature Attribution for Tree Ensembles
• Sanity Checks for Saliency Maps
• On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper)

Cited by

• Hybrid Attribution Priors for Explainable and Robust Model Training

Related

• Hybrid Attribution Priors for Explainable and Robust Model Training
• Controlling Learned Effects to Reduce Spurious Correlations in Text Classifiers
• Learning Deep Attribution Priors Based On Prior Knowledge
• Benchmarking Attribution Methods with Relative Feature Importance
• Distribution-Based Feature Attribution for Explaining the Predictions of Any Classifier