Gating-adapted Wavelet Multiresolution Analysis for Exposure Sequence Modeling in CTR prediction

TL;DR

This paper introduces Gama, a gating-adapted wavelet multiresolution analysis method that denoises long exposure sequences efficiently, capturing multi-dimensional user interests for improved CTR prediction with low latency, suitable for large-scale industrial deployment.

Contribution

It is the first to integrate non-parametric multiresolution analysis into deep neural networks for exposure sequence modeling, addressing noise and latency issues in CTR prediction.

Findings

Gama effectively denoises long exposure sequences.

It captures multi-dimensional user interests adaptively.

Deployed in industrial recommender system serving hundreds of millions of users.

Abstract

The exposure sequence is being actively studied for user interest modeling in Click-Through Rate (CTR) prediction. However, the existing methods for exposure sequence modeling bring extensive computational burden and neglect noise problems, resulting in an excessively latency and the limited performance in online recommenders. In this paper, we propose to address the high latency and noise problems via Gating-adapted wavelet multiresolution analysis (Gama), which can effectively denoise the extremely long exposure sequence and adaptively capture the implied multi-dimension user interest with linear computational complexity. This is the first attempt to integrate non-parametric multiresolution analysis technique into deep neural networks to model user exposure sequence. Extensive experiments on large scale benchmark dataset and real production dataset confirm the effectiveness of Gama for exposure sequence modeling, especially in cold-start scenarios. Benefited from its low latency and high effecitveness, Gama has been deployed in our real large-scale industrial recommender, successfully serving over hundreds of millions users.