Neural News Recommendation with Attentive Multi-View Learning

Wu, Chuhan; Wu, Fangzhao; An, Mingxiao; Huang, Jianqiang; Huang, Yongfeng; Xie, Xing

doi:10.24963/ijcai.2019/536

Cited by 170 publications

(182 citation statements)

References 3 publications

Supporting

Mentioning

182

Contrasting

Order By: Relevance

“…A straightforward way [20,38,39] is to concatenate the multiple modality features, which is equivalent to giving a fixed importance weight to each modality regardless of different items. A conceivable improvement [14,31] is to dynamically distinguish the contributions of different modalities through an attention mechanism. However, features of multiple modalities may contain redundant information, which should be eliminated when computing the different contributions of modalities.…”

Section: Multimodal Attention Networkmentioning

confidence: 99%

Adversarial Multimodal Representation Learning for Click-Through Rate Prediction

Wang

Tan

et al. 2020

Proceedings of the Web Conference 2020

View full text Add to dashboard Cite

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 modalityinvariant 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.

show abstract

Section: Multimodal Attention Networkmentioning

confidence: 99%

Adversarial Multimodal Representation Learning for Click-Through Rate Prediction

Wang

Tan

et al. 2020

Proceedings of the Web Conference 2020

View full text Add to dashboard Cite

show abstract

“…It captures the long-term user interest via user ID embedding and the short-term user interest from the latest news click behaviors via GRU. For measuring the relevance between user interest and news content, dot product of user and news representation vectors is widely used (Okura et al, 2017;Wu et al, 2019a;. Some methods also explore cosine similarity (Zhu et al, 2019b), feed-forward network , feature-interaction network (Lian et al, 2018).…”

Section: News Recommendationmentioning

confidence: 99%

“…Following previous works (Wu et al, 2019a;, the news recommendation model in our method can be decomposed into two core submodels, i.e., a news model to learn news representations and a user model to learn user representations.…”

Section: Basic News Recommendation Modelmentioning

confidence: 99%

“…Thus, personalized news recommendation, which aims to display news articles to users based on their personal interest, is a useful technique to improve user experience and has been widely used in many online news services (Wu et al, 2019b). The research of news recommendation has attracted many attentions from both academic and industrial fields (Okura et al, 2017;Lian et al, 2018;Wu et al, 2019a).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Privacy-Preserving News Recommendation Model Learning

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

Self Cite

107

View full text Add to dashboard Cite

News recommendation aims to display news articles to users based on their personal interest. Existing news recommendation methods rely on centralized storage of user behavior data for model training, which may lead to privacy concerns and risks due to the privacy-sensitive nature of user behaviors. In this paper, we propose a privacy-preserving method for news recommendation model training based on federated learning, where the user behavior data is locally stored on user devices. Our method can leverage the useful information in the behaviors of massive number users to train accurate news recommendation models and meanwhile remove the need of centralized storage of them. More specifically, on each user device we keep a local copy of the news recommendation model, and compute gradients of the local model based on the user behaviors in this device. The local gradients from a group of randomly selected users are uploaded to server, which are further aggregated to update the global model in the server. Since the model gradients may contain some implicit private information, we apply local differential privacy (LDP) to them before uploading for better privacy protection. The updated global model is then distributed to each user device for local model update. We repeat this process for multiple rounds. Extensive experiments on a real-world dataset show the effectiveness of our method in news recommendation model training with privacy protection.

show abstract

“…The (Wu et al, 2019b). There are also many options for the user encoder, such as GRU (Hidasi et al, 2016), attention network (Wu et al, 2019a) and Transformer (Sun et al, 2019). In these existing methods, their user models are trained in an end-to-end way using the labeled data of target task, which can only capture task-specific information.…”

Section: Introductionmentioning

confidence: 99%

PTUM: Pre-training User Model from Unlabeled User Behaviors via Self-supervision

Wu¹,

Wu²,

Qi³

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

Self Cite

View full text Add to dashboard Cite

User modeling is critical for many personalized web services. Many existing methods model users based on their behaviors and the labeled data of target tasks. However, these methods cannot exploit useful information in unlabeled user behavior data, and their performance may be not optimal when labeled data is scarce. Motivated by pre-trained language models which are pre-trained on large-scale unlabeled corpus to empower many downstream tasks, in this paper we propose to pretrain user models from large-scale unlabeled user behaviors data. We propose two selfsupervision tasks for user model pre-training. The first one is masked behavior prediction, which can model the relatedness between historical behaviors. The second one is next K behavior prediction, which can model the relatedness between past and future behaviors. The pre-trained user models are finetuned in downstream tasks to learn task-specific user representations. Experimental results on two realworld datasets validate the effectiveness of our proposed user model pre-training method.

show abstract

Neural News Recommendation with Attentive Multi-View Learning

Abstract: Personalized news recommendation is very impor-

Cited by 170 publications

References 3 publications

Adversarial Multimodal Representation Learning for Click-Through Rate Prediction

Adversarial Multimodal Representation Learning for Click-Through Rate Prediction

Privacy-Preserving News Recommendation Model Learning

PTUM: Pre-training User Model from Unlabeled User Behaviors via Self-supervision

Contact Info

Product

Resources

About