Adversarial Multimodal Representation Learning for Click-Through Rate Prediction

模式 模态(人机交互) 计算机科学 对抗制 人工智能 多模式学习 机器学习 互补性(分子生物学) 代表(政治) 冗余(工程) 人工神经网络 不变(物理) 自然语言处理 数学 遗传学 生物 政治 操作系统 政治学 社会学 法学 数学物理 社会科学
作者
Xiang Li,Chao Wang,Jiwei Tan,Xiaoyi Zeng,Dan Ou,Dan Ou,Bo Zheng
标识
DOI:10.1145/3366423.3380163
摘要

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.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
潘妮花花完成签到 ,获得积分10
刚刚
HAYZ666完成签到,获得积分20
刚刚
2秒前
一二发布了新的文献求助10
3秒前
高大的小土豆完成签到,获得积分10
3秒前
领导范儿应助研友_ZG4ml8采纳,获得10
4秒前
5秒前
6秒前
7秒前
HBXAurora发布了新的文献求助10
8秒前
yanhuazi完成签到,获得积分10
8秒前
030发布了新的文献求助10
8秒前
王王泽发布了新的文献求助10
10秒前
Yan123456完成签到,获得积分10
10秒前
11秒前
11秒前
潇洒的千山完成签到,获得积分20
11秒前
无花果应助一二采纳,获得10
13秒前
13秒前
喜悦的丹妗完成签到,获得积分10
15秒前
cz发布了新的文献求助10
16秒前
18秒前
Akim应助yjw采纳,获得10
18秒前
研友_ZG4ml8发布了新的文献求助10
19秒前
火华完成签到 ,获得积分10
20秒前
独弦清音发布了新的文献求助10
21秒前
科研通AI2S应助科研通管家采纳,获得10
22秒前
Orange应助科研通管家采纳,获得10
22秒前
CodeCraft应助科研通管家采纳,获得10
22秒前
SciGPT应助科研通管家采纳,获得10
22秒前
爆米花应助科研通管家采纳,获得10
22秒前
hui完成签到,获得积分10
23秒前
香蕉觅云应助生信难民采纳,获得10
24秒前
25秒前
cz完成签到,获得积分20
29秒前
FF发布了新的文献求助10
30秒前
31秒前
37秒前
CodeCraft应助研友_ZG4ml8采纳,获得10
37秒前
尼克发布了新的文献求助30
38秒前
高分求助中
Sustainability in Tides Chemistry 2800
The Young builders of New china : the visit of the delegation of the WFDY to the Chinese People's Republic 1000
Rechtsphilosophie 1000
Bayesian Models of Cognition:Reverse Engineering the Mind 888
Le dégorgement réflexe des Acridiens 800
Defense against predation 800
Very-high-order BVD Schemes Using β-variable THINC Method 568
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3134969
求助须知:如何正确求助?哪些是违规求助? 2785927
关于积分的说明 7774469
捐赠科研通 2441746
什么是DOI,文献DOI怎么找? 1298163
科研通“疑难数据库(出版商)”最低求助积分说明 625088
版权声明 600825