Timezone: »
Imbalanced datasets are commonplace in modern machine learning problems. The presence of under-represented classes or groups with sensitive attributes results in concerns about generalization and fairness. Such concerns are further exacerbated by the fact that large capacity deep nets can perfectly fit the training data and appear to achieve perfect accuracy and fairness during training, but perform poorly during test. To address these challenges, we propose AutoBalance, a bi-level optimization framework that automatically designs a training loss function to optimize a blend of accuracy and fairness-seeking objectives. Specifically, a lower-level problem trains the model weights, and an upper-level problem tunes the loss function by monitoring and optimizing the desired objective over the validation data. Our loss design enables personalized treatment for classes/groups by employing a parametric cross-entropy loss and individualized data augmentation schemes. We evaluate the benefits and performance of our approach for the application scenarios of imbalanced and group-sensitive classification. Extensive empirical evaluations demonstrate the benefits of AutoBalance over state-of-the-art approaches. Our experimental findings are complemented with theoretical insights on loss function design and the benefits of the train-validation split. All code is available open-source.
Author Information
Mingchen Li (University of California, Riverside)
Xuechen Zhang (UC Riverside)
Christos Thrampoulidis (University of British Columbia)
Jiasi Chen (University of California, Riverside)
Samet Oymak (University of California, Riverside)
More from the Same Authors
-
2022 : On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data »
Tina Behnia · Ganesh Ramachandra Kini · Vala Vakilian · Christos Thrampoulidis -
2022 : Generalization of Decentralized Gradient Descent with Separable Data »
Hossein Taheri · Christos Thrampoulidis -
2022 : Fast Convergence of Random Reshuffling under Interpolation and the Polyak-Ćojasiewicz Condition »
Chen Fan · Christos Thrampoulidis · Mark Schmidt -
2022 Poster: Imbalance Trouble: Revisiting Neural-Collapse Geometry »
Christos Thrampoulidis · Ganesh Ramachandra Kini · Vala Vakilian · Tina Behnia -
2022 Poster: Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently »
Haoyuan Sun · Kwangjun Ahn · Christos Thrampoulidis · Navid Azizan -
2022 Poster: Non-asymptotic and Accurate Learning of Nonlinear Dynamical Systems »
Yahya Sattar · Samet Oymak -
2021 Poster: UCB-based Algorithms for Multinomial Logistic Regression Bandits »
Sanae Amani · Christos Thrampoulidis -
2021 Poster: Label-Imbalanced and Group-Sensitive Classification under Overparameterization »
Ganesh Ramachandra Kini · Orestis Paraskevas · Samet Oymak · Christos Thrampoulidis -
2021 Poster: Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation »
Ke Wang · Vidya Muthukumar · Christos Thrampoulidis -
2021 Poster: Towards Sample-efficient Overparameterized Meta-learning »
Yue Sun · Adhyyan Narang · Ibrahim Gulluk · Samet Oymak · Maryam Fazel -
2020 Poster: Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View »
Christos Thrampoulidis · Samet Oymak · Mahdi Soltanolkotabi -
2020 Poster: Stage-wise Conservative Linear Bandits »
Ahmadreza Moradipari · Christos Thrampoulidis · Mahnoosh Alizadeh