ICSE 2024
Fri 12 - Sun 21 April 2024 Lisbon, Portugal
Wed 17 Apr 2024 16:00 - 16:15 at Pequeno Auditório - Program Repair 3 Chair(s): Alcides Fonseca

Deep Neural Networks (DNNs), an emerging software technology, have achieved impressive results in a variety of fields. However, the discriminatory behaviors towards certain groups (a.k.a. unfairness) of DNN models increasingly become a social concern, especially in high-stake applications such as loan approval and criminal risk assessment. Although there has been a number of works to improve model fairness, most of them adopt an adversary to either expand the model architecture or augment training data, which introduces excessive computational overhead. Recent work diagnoses responsible unfair neurons first and fixes them with selective retraining. Unfortunately, existing diagnosis process is time-consuming due to multi-step training sample analysis and selective retraining may cause a performance bottleneck due to indirectly adjusting unfair neurons on biased samples. In this paper, we propose Responsible UNfair NEuron Repair (RUNNER) that improves existing works in three key aspects: (1) efficiency: we design the Importance-based Neuron Diagnosis that identifies responsible unfair neurons in one step with a novel importance criterion of neurons; (2) effectiveness: we design the Neuron Stabilizing Retraining by adding a loss term that measures the activation distance of responsible unfair neurons from different subgroups in all sources; (3) generalization: we investigate the effectiveness on both structured tabular data and large-scale unstructured image data, which is often ignored in prior studies. Our extensive experiments across 5 datasets show that RUUNER can effectively and efficiently diagnose and repair the DNNs regarding unfairness. On average, our approach significantly reduces computing overhead from 341.7s to 29.65s, and achieves improved fairness up to 79.3%. Besides, RUNNER also keeps state-of-the-art results on the unstructured dataset.

Wed 17 Apr

Displayed time zone: Lisbon change

16:00 - 17:30
Program Repair 3Research Track at Pequeno Auditório
Chair(s): Alcides Fonseca University of Lisbon
16:00
15m
Talk
RUNNER: Responsible UNfair NEuron Repair for Enhancing Deep Neural Network Fairness
Research Track
Li Tianlin Nanyang Technological University, Yue Cao Nanyang Technological University, Jian Zhang Nanyang Technological University, Shiqian Zhao Nanyang Technological University, Yihao Huang East China Normal University, Aishan Liu Beihang University; Institute of Dataspace, Qing Guo IHPC and CFAR at A*STAR, Singapore, Yang Liu Nanyang Technological University
16:15
15m
Talk
ITER: Iterative Neural Repair for Multi-Location Patches
Research Track
He Ye Carnegie Mellon University, Martin Monperrus KTH Royal Institute of Technology
16:30
15m
Talk
Out of Context: How important is Local Context in Neural Program Repair?
Research Track
Julian Prenner Free University of Bozen-Bolzano, Romain Robbes CNRS, LaBRI, University of Bordeaux
16:45
15m
Talk
Out of Sight, Out of Mind: Better Automatic Vulnerability Repair by Broadening Input Ranges and Sources
Research Track
Xin Zhou Singapore Management University, Singapore, Kisub Kim Singapore Management University, Singapore, Bowen Xu North Carolina State University, DongGyun Han Royal Holloway, University of London, David Lo Singapore Management University
17:00
15m
Talk
Strengthening Supply Chain Security with Fine-grained Safe Patch Identification
Research Track
Luo Changhua The Chinese University of Hong Kong, Wei Meng Chinese University of Hong Kong, Shuai Wang The Hong Kong University of Science and Technology