• Home
  • Search
  • Adversarial Filtering Modeling on Long-term User Behavior Sequences for Click-Through Rate Prediction
  • Open Access IconOpen Access
  • Cite Icon8
  • https://doi.org/10.1145/3477495.3531788Copy DOI Icon

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

  • Jul 6, 2022
  • Xiaochen Li +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
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.

Similar Papers
  • Conference Article

Hierarchical User Long-term Behavior Modeling for Click-Through Rate Prediction

  • Jul 13, 2025
  • Mao Pan +6
  • Conference Article
  • Citations2

Time-aware Multi-layer Interest Extraction Network for Click-Through Rate Prediction

  • Mar 01, 2022
  • Guoan Wang +1
  • Conference Article
  • Citations3

FedUD: Exploiting Unaligned Data for Cross-Platform Federated Click-Through Rate Prediction

  • Jul 10, 2024
  • Wentao Ouyang +3
  • Conference Article
  • Citations290

Practice on Long Sequential User Behavior Modeling for Click-Through Rate Prediction

  • Jul 25, 2019
  • Qi Pi +4
  • Book Chapter
  • Citations4

A Non-sequential Approach to Deep User Interest Model for CTR Prediction

  • Jan 01, 2022
  • Keke Zhao +3
  • Conference Article
  • Citations4

IUI: Intent-Enhanced User Interest Modeling for Click-Through Rate Prediction

  • Oct 21, 2023
  • Mao Pan +7
  • Conference Article
  • Citations58

Multi-Interactive Attention Network for Fine-grained Feature Learning in CTR Prediction

  • Mar 08, 2021
  • Kai Zhang +7
  • Conference Article
  • Citations3

A Novel Efficient Unclick Behavior Modeling Framework for Click-Through Rate Prediction

  • Oct 01, 2022
  • Jiao He +2
  • Conference Article
  • Citations5

AIE: Auction Information Enhanced Framework for CTR Prediction in Online Advertising

  • Oct 08, 2024
  • Yang Yang +8
  • Conference Article
  • Citations18

Clustering based Behavior Sampling with Long Sequential Data for CTR Prediction

  • Jul 06, 2022
  • Yuren Zhang +6
  • Conference Article
  • Citations293

Deep Session Interest Network for Click-Through Rate Prediction

  • Aug 01, 2019
  • Yufei Feng +6
  • Research Article

TriSeqNet: Tri-dimensional sequential fusion network for triple relationships in CTR prediction

  • Dec 08, 2025
  • Intelligent Data Analysis: An International Journal
  • Yang Wu +3
  • Conference Article
  • Citations36

Deep Time-Aware Item Evolution Network for Click-Through Rate Prediction

  • Oct 19, 2020
  • Xiang Li +5
  • Conference Article
  • Citations60

MiNet

  • Oct 19, 2020
  • Wentao Ouyang +7
  • Research Article
  • Citations1088

Deep Interest Evolution Network for Click-Through Rate Prediction

  • Jul 17, 2019
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Guorui Zhou +7
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.