Simplifying neural network training under class imbalance
Improving neural network performance on imbalanced datasets by tuning standard training components, without specialized methods.
Real-world datasets are often highly class-imbalanced, which can adversely impact the performance of deep learning models. The majority of research on training neural networks under class imbalance has focused on specialized loss functions, sampling techniques or two-stage training procedures. Notably, we demonstrate that simply tuning existing components of standard deep learning pipelines, such as the batch size, data augmentation, optimizer and label smoothing, can achieve state-of-the-art performance without any such specialized class imbalance methods. We also provide key prescriptions and considerations for training under class imbalance and an understanding of why imbalanced methods succeed or fail.
Latest publications
Leveraging parameter space symmetries for reasoning skill transfer in LLMs
Utilizing an alignment-first strategy to transfer advanced reasoning skills to a non-reasoning model.
NeurIPSGPO: learning from critical steps to improve LLM reasoning
A novel fine-tuning strategy designed to improve LLM multi-step reasoning capabilities by focusing on pivotal moments.
NeurIPSSpatio-temporal directed graph learning for Account Takeover fraud detection
A framework that reformulates ATO detection as spatio-temporal node classification.
NeurIPS