DeepFM: A Factorization-Machine based Neural Network for CTR Prediction

Guo, Huifeng; Tang, Ruiming; Ye, Yunming; Li, Zhenguo; He, Xiuqiang

doi:10.24963/ijcai.2017/239

Cited by 1,704 publications

(1,316 citation statements)

References 19 publications

(11 reference statements)

Supporting

Mentioning

1,212

Contrasting

Unclassified

Order By: Relevance

“…The representative methods are Matrix Factorization (MF) [20] and Factorization Machine (FM) [29]. Neural FM [16] and DeepFM [15] have improved FM's representation ability with deep neural networks. [3,13,18] utilize user's implicit feedback, commonly optimizing BPR loss [30].…”

Section: Related Workmentioning

confidence: 99%

Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems

Lei

Miao

et al. 2020

Proceedings of the 13th International Conference on Web Search and Data Mining

187

387

View full text Add to dashboard Cite

Recommender systems are embracing conversational technologies to obtain user preferences dynamically, and to overcome inherent limitations of their static models. A successful Conversational Recommender System (CRS) requires proper handling of interactions between conversation and recommendation. We argue that three fundamental problems need to be solved: 1) what questions to ask regarding item attributes, 2) when to recommend items, and 3) how to adapt to the users' online feedback. To the best of our knowledge, there lacks a unified framework that addresses these problems.In this work, we fill this missing interaction framework gap by proposing a new CRS framework named Estimation-Action-Reflection, or EAR, which consists of three stages to better converse with users. (1) Estimation, which builds predictive models to estimate user preference on both items and item attributes; (2) Action, which learns a dialogue policy to determine whether to ask attributes or recommend items, based on Estimation stage and conversation history; and (3) Reflection, which updates the recommender model when a user rejects the recommendations made by the Action stage. We present two conversation scenarios on binary and enumerated questions, and conduct extensive experiments on two datasets from Yelp and LastFM, for each scenario, respectively. Our experiments demonstrate significant improvements over the state-of-the-art method CRM [32], corresponding to fewer conversation turns and a higher level of recommendation hits. CCS CONCEPTS• Information systems → Users and interactive retrieval; Recommender systems; Personalization; • Human-centered computing → Interactive systems and tools.

show abstract

Section: Related Workmentioning

confidence: 99%

Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems

Lei

Miao

et al. 2020

Proceedings of the 13th International Conference on Web Search and Data Mining

187

387

View full text Add to dashboard Cite

show abstract

“…• DeepFM [26] is also a general deep model for recommendation, which combines a component of factorization machines and a component of deep All the baseline models are based on deep neural networks. DMF is a collaborative filtering based model, while the others are all content based.…”

Section: Baselinesmentioning

confidence: 99%

Graph neural news recommendation with long-term and short-term interest modeling

Shi

et al. 2020

Information Processing & Management

162

View full text Add to dashboard Cite

With the information explosion of news articles, personalized news recommendation has become important for users to quickly find news that they are interested in. Existing methods on news recommendation mainly include collaborative filtering methods which rely on direct user-item interactions and content based methods which characterize the content of user reading history. Although these methods have achieved good performances, they still suffer from data sparse problem, since most of them fail to extensively exploit high-order structure information in news recommendation systems. In this paper, we propose to build a heterogeneous graph to explicitly model the interactions among users, news and latent topics. The incorporated topic information would help indicate a user's interest and alleviate the sparsity of user-item interactions. Then we take advantage of graph neural networks to learn user and news representations that encode high-order structure information by propagating embeddings over the graph. The learned user embeddings with complete historic user clicks capture the users' long-term interests. We also consider a user's short-term interest using the recent reading history with an attention based LSTM model. Experimental results on real-world datasets show that our proposed model significantly outperforms state-of-the-art methods on news recommendation.

show abstract

“…Some works on another line try to model the second-order and high-order interactions jointly via a hybrid architectures. The Wide&Deep [2] and DeepFM [6] contain a wide part to model the low-order interaction and a deep part to model the high-order interaction. However, all these approaches leveraging DNN learn the high-order feature interactions in an implicit, bit-wise way and therefore lack good model explainability.…”

Section: Feature Interaction In Ctr Predictionmentioning

confidence: 99%

Fi-GNN

Cui

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

140

View full text Add to dashboard Cite

Click-through rate (CTR) prediction is an essential task in web applications such as online advertising and recommender systems, whose features are usually in multi-field form. The key of this task is to model feature interactions among different feature fields. Recently proposed deep learning based models follow a general paradigm: raw sparse input multi-filed features are first mapped into dense field embedding vectors, and then simply concatenated together to feed into deep neural networks (DNN) or other specifically designed networks to learn high-order feature interactions. However, the simple unstructured combination of feature fields will inevitably limit the capability to model sophisticated interactions among different fields in a sufficiently flexible and explicit fashion.In this work, we propose to represent the multi-field features in a graph structure intuitively, where each node corresponds to a feature field and different fields can interact through edges. The task of modeling feature interactions can be thus converted to modeling node interactions on the corresponding graph. To this end, we design a novel model Feature Interaction Graph Neural Networks (Fi-GNN). Taking advantage of the strong representative power of graphs, our proposed model can not only model sophisticated feature interactions in a flexible and explicit fashion, but also provide good model explanations for CTR prediction. Experimental results on two real-world datasets show its superiority over the state-of-the-arts.

show abstract

DeepFM: A Factorization-Machine based Neural Network for CTR Prediction

Cited by 1,704 publications

References 19 publications

Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems

Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems

Graph neural news recommendation with long-term and short-term interest modeling

Fi-GNN

Contact Info

Product

Resources

About