Adversarial Filtering Modeling on Long-term User Behavior Sequences for Click-Through Rate Prediction

TL;DR

This paper introduces ADFM, an adversarial filtering approach that effectively models long-term user behavior sequences for CTR prediction, balancing performance and computational cost.

Contribution

The paper proposes a novel hierarchical adversarial filtering model that reduces noise in long-term user behavior data for improved CTR prediction accuracy.

Findings

Significant performance improvements over state-of-the-art models.

Effective noise reduction in long-term behavior sequences.

Validated on both public and industrial datasets.

Abstract

Rich user behavior information is of great importance for capturing and understanding user interest in click-through rate (CTR) prediction. To improve the richness, collecting long-term behaviors becomes a typical approach in academy and industry but at the cost of increasing online storage and latency. Recently, researchers have proposed several approaches to shorten long-term behavior sequence and then model user interests. These approaches reduce online cost efficiently but do not well handle the noisy information in long-term user behavior, which may deteriorate the performance of CTR prediction significantly. To obtain better cost/performance trade-off, we propose a novel Adversarial Filtering Model (ADFM) to model long-term user behavior. ADFM uses a hierarchical aggregation representation to compress raw behavior sequence and then learns to remove useless behavior information with an adversarial filtering mechanism. The selected user behaviors are fed into interest extraction module for CTR prediction. Experimental results on public datasets and industrial dataset demonstrate that our method achieves significant improvements over state-of-the-art models.