CLAX: Fast and Flexible Neural Click Models in JAX

TL;DR

CLAX is a JAX-based library that enables fast, flexible, and gradient-based optimization of classic and neural click models, significantly improving efficiency and modularity for large-scale user behavior analysis.

Contribution

It introduces a novel gradient-based optimization approach for probabilistic graphical models in click modeling, replacing EM, with a modular design for easy integration of components.

Findings

Achieves full dataset processing in approximately 2 hours on a single GPU.

Implements ten classic click models with improved efficiency.

Enables end-to-end optimization of complex click models.

Abstract

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