Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019
This work provides a standardized benchmark and modular framework for evaluating AutoDL methods, benefiting researchers and practitioners in machine learning by enabling fair comparisons and ablation studies, though it is incremental as it builds on existing techniques without introducing novel components.
The paper tackled the problem of fairly comparing AutoML solutions for deep learning across multiple data modalities by organizing the ChaLearn AutoDL challenge, where winning solutions relied on fine-tuned pre-trained networks and achieved results quickly under limited time and computational constraints, with post-challenge tests showing no improvements beyond the imposed limits.
This paper reports the results and post-challenge analyses of ChaLearn's AutoDL challenge series, which helped sorting out a profusion of AutoML solutions for Deep Learning (DL) that had been introduced in a variety of settings, but lacked fair comparisons. All input data modalities (time series, images, videos, text, tabular) were formatted as tensors and all tasks were multi-label classification problems. Code submissions were executed on hidden tasks, with limited time and computational resources, pushing solutions that get results quickly. In this setting, DL methods dominated, though popular Neural Architecture Search (NAS) was impractical. Solutions relied on fine-tuned pre-trained networks, with architectures matching data modality. Post-challenge tests did not reveal improvements beyond the imposed time limit. While no component is particularly original or novel, a high level modular organization emerged featuring a "meta-learner", "data ingestor", "model selector", "model/learner", and "evaluator". This modularity enabled ablation studies, which revealed the importance of (off-platform) meta-learning, ensembling, and efficient data management. Experiments on heterogeneous module combinations further confirm the (local) optimality of the winning solutions. Our challenge legacy includes an ever-lasting benchmark (http://autodl.chalearn.org), the open-sourced code of the winners, and a free "AutoDL self-service".