# Adversarial Multimodal Representation Learning for Click-Through Rate Prediction

arXiv: https://arxiv.org/abs/2003.07162 · HTML: https://mlsanity.com/paper/2003.07162/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2020.

## Built on by (most cited first, 18 of 18)

- [User Response Prediction in Online Advertising](https://mlsanity.com/paper/2101.02342/) (2021)
- [Cross-Contrastive Clustering for Multimodal Attributed Graphs with Dual Graph Filtering](https://mlsanity.com/paper/2511.20030/) (2025)
- [Causality-based CTR Prediction using Graph Neural Networks](https://mlsanity.com/paper/2301.12762/) (2023)
- [MOON2.0: Dynamic Modality-balanced Multimodal Representation Learning for E-commerce Product Understanding](https://mlsanity.com/paper/2511.12449/) (2025)
- [One-stage Modality Distillation for Incomplete Multimodal Learning](https://mlsanity.com/paper/2309.08204/) (2023)
- [Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Prediction](https://mlsanity.com/paper/2508.21460/) (2025)
- [Micro-video Tagging via Jointly Modeling Social Influence and Tag Relation](https://mlsanity.com/paper/2303.08318/) (2023)
- [Features Fusion Framework for Multimodal Irregular Time-series Events](https://mlsanity.com/paper/2209.01728/) (2022)
- [DashCLIP: Leveraging multimodal models for generating semantic embeddings for DoorDash](https://mlsanity.com/paper/2504.07110/) (2025)
- [Deep Intention-Aware Network for Click-Through Rate Prediction](https://mlsanity.com/paper/2211.08650/) (2022)
- [MultiHead MultiModal Deep Interest Recommendation Network](https://mlsanity.com/paper/2110.10205/) (2021)
- [Learning Discriminative Visual-Text Representation for Polyp Re-Identification](https://mlsanity.com/paper/2307.10625/) (2023)
- [AdSEE: Investigating the Impact of Image Style Editing on Advertisement Attractiveness](https://mlsanity.com/paper/2309.08159/) (2023)
- [Complementary Information Mutual Learning for Multimodality Medical Image Segmentation](https://mlsanity.com/paper/2401.02717/) (2024)
- [GCM-Net: Graph-enhanced Cross-Modal Infusion with a Metaheuristic-Driven Network for Video Sentiment and Emotion Analysis](https://mlsanity.com/paper/2410.12828/) (2024)
- [Conversion rate prediction in online advertising: modeling techniques, performance evaluation and future directions](https://mlsanity.com/paper/2512.01171/) (2025)
- [Toward a benchmark for CTR prediction in online advertising: datasets, evaluation protocols and perspectives](https://mlsanity.com/paper/2512.01179/) (2025)
- [PinDCO: Whole-Page Aware Dynamic Creative Optimization at Scale](https://mlsanity.com/paper/2609.11943/) (2026)

## Abstract (arXiv)

For better user experience and business effectiveness, Click-Through Rate (CTR) prediction has been one of the most important tasks in E-commerce. Although extensive CTR prediction models have been proposed, learning good representation of items from multimodal features is still less investigated, considering an item in E-commerce usually contains multiple heterogeneous modalities. Previous works either concatenate the multiple modality features, that is equivalent to giving a fixed importance weight to each modality; or learn dynamic weights of different modalities for different items through technique like attention mechanism. However, a problem is that there usually exists common redundant information across multiple modalities. The dynamic weights of different modalities computed by using the redundant information may not correctly reflect the different importance of each modality. To address this, we explore the complementarity and redundancy of modalities by considering modality-specific and modality-invariant features differently. We propose a novel Multimodal Adversarial Representation Network (MARN) for the CTR prediction task. A multimodal attention network first calculates the weights of multiple modalities for each item according to its modality-specific features. Then a multimodal adversarial network learns modality-invariant representations where a double-discriminators strategy is introduced. Finally, we achieve the multimodal item representations by combining both modality-specific and modality-invariant representations. We conduct extensive experiments on both public and industrial datasets, and the proposed method consistently achieves remarkable improvements to the state-of-the-art methods. Moreover, the approach has been deployed in an operational E-commerce system and online A/B testing further demonstrates the effectiveness.