<ul><li>Applying fairness criteria to model pruning to address algorithmic biases and social justice concerns.</li><li>Introducing a framework for fair model pruning that optimizes the pruning mask and weight update processes with fairness constraints.</li><li>Demonstrating the superiority of the proposed method in maintaining model fairness, performance, and efficiency compared to mainstream pruning strategies.</li><li>Validating the approach through experiments on various datasets and scenarios.</li></ul>

Integrating Fairness and Model Pruning Through Bi-level Optimization

Discover more