• Home
  • Search
  • Multi-Interactive Attention Network for Fine-grained Feature Learning in CTR Prediction
  • Open Access IconOpen Access
  • Cite Icon58
  • https://doi.org/10.1145/3437963.3441761Copy DOI Icon

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

  • Mar 8, 2021
  • Kai Zhang +7 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In the Click-Through Rate (CTR) prediction scenario, user's sequential behaviors are well utilized to capture the user interest in the recent literature. However, despite being extensively studied, these sequential methods still suffer from three limitations. First, existing methods mostly utilize attention on the behavior of users, which is not always suitable for CTR prediction, because users often click on new products that are irrelevant to any historical behaviors. Second, in the real scenario, there are numerous users that have operations a long time ago, but turn relatively inactive in recent times. Thus, it is hard to precisely capture user's current preferences through early behaviors. Third, multiple representations of user's historical behaviors in different feature subspaces are largely ignored. To remedy these issues, we propose a Multi-Interactive Attention Network (MIAN) to comprehensively extract the latent relationship among all kinds of fine-grained features (e.g., gender, age and occupation in user-profile). Specifically, MIAN contains a Multi-Interactive Layer (MIL) that integrates three local interaction modules to capture multiple representations of user preference through sequential behaviors and simultaneously utilize the fine-grained user-specific as well as context information. In addition, we design a Global Interaction Module (GIM) to learn the high-order interactions and balance the different impacts of multiple features. Finally, Offline experiment results from three datasets, together with an Online A/B test in a large-scale recommendation system, demonstrate the effectiveness of our proposed approach.

Similar Papers
  • Conference Article
  • Citations5

An Attention-based Deep Network for CTR Prediction

  • Feb 15, 2020
  • Hailong Zhang +2
  • Conference Article
  • Citations60

MiNet

  • Oct 19, 2020
  • Wentao Ouyang +7
  • Conference Article
  • Citations16

Click-through rate prediction with the user memory network

  • Aug 05, 2019
  • Wentao Ouyang +5
  • Conference Article
  • Citations4

Enhancing CTR Prediction through Sequential Recommendation Pre-training: Introducing the SRP4CTR framework

  • Oct 21, 2024
  • Ruidong Han +6
  • Conference Article
  • Citations8

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

  • Jul 06, 2022
  • Xiaochen Li +3
  • PDF
  • Research Article
  • Citations11

XGBDeepFM for CTR Predictions in Mobile Advertising Benefits from Ad Context

  • Apr 27, 2020
  • Mathematical Problems in Engineering
  • Han An +1
  • Conference Article
  • Citations293

Deep Session Interest Network for Click-Through Rate Prediction

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

PRECTR: A Synergistic Framework for Integrating Personalized Search Relevance Matching and CTR Prediction

  • May 08, 2025
  • Rong Chen +4
  • Conference Article
  • Citations124

User Behavior Retrieval for Click-Through Rate Prediction

  • Jul 25, 2020
  • Jiarui Qin +5
  • PDF
  • Research Article
  • Citations1

Feature-Interaction-Enhanced Sequential Transformer for Click-Through Rate Prediction

  • Mar 26, 2024
  • Applied Sciences
  • Quan Yuan +4
  • Research Article
  • Citations7

A knowledge distillation-based deep interaction compressed network for CTR prediction

  • Jun 08, 2023
  • Knowledge-Based Systems
  • Fei Guan +2
  • 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
  • Citations2

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

  • Mar 01, 2022
  • Guoan Wang +1
  • Conference Article
  • Citations15

MTBRN

  • Oct 19, 2020
  • Yufei Feng +7
  • Conference Article
  • Citations2

CSPM: A Contrastive Spatiotemporal Preference Model for CTR Prediction in On-Demand Food Delivery Services

  • Oct 21, 2023
  • Guyu Jiang +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.