CLAX: Fast and Flexible Neural Click Models in JAX
This work provides a fast and flexible tool for industry practitioners and researchers to improve ranking performance and develop new click models, though it is incremental in optimizing existing models.
The paper tackles the gap in neural click models by introducing CLAX, a JAX-based library that replaces EM-based optimization with gradient-based methods, enabling efficient training on large datasets like Baidu-ULTR with over a billion sessions in about 2 hours on a single GPU.
CLAX is a JAX-based library that implements classic click models using modern gradient-based optimization. While neural click models have emerged over the past decade, complex click models based on probabilistic graphical models (PGMs) have not systematically adopted gradient-based optimization, preventing practitioners from leveraging modern deep learning frameworks while preserving the interpretability of classic models. CLAX addresses this gap by replacing EM-based optimization with direct gradient-based optimization in a numerically stable manner. The framework's modular design enables the integration of any component, from embeddings and deep networks to custom modules, into classic click models for end-to-end optimization. We demonstrate CLAX's efficiency by running experiments on the full Baidu-ULTR dataset comprising over a billion user sessions in $\approx$ 2 hours on a single GPU, orders of magnitude faster than traditional EM approaches. CLAX implements ten classic click models, serving both industry practitioners seeking to understand user behavior and improve ranking performance at scale and researchers developing new click models. CLAX is available at: https://github.com/philipphager/clax