DELF: A Dual-Embedding based Deep Latent Factor Model for Recommendation

By Weiyu Cheng, Yanyan Shen, Yanmin Zhu, Linpeng Huang. 2018

60 citations recorded by the source corpus.

Among various recommendation methods, latent factor models are usually considered to be state-of-the-art techniques, which aim to learn user and item embeddings for predicting user-item preferences. When applying latent factor models to recommendation with implicit feedback, the quality of embeddings always suffers from inadequate positive feedback and noisy negative feedback. Inspired by the idea of NSVD that represents users based on their interacted items, this paper proposes a dual-embedding based deep latent factor model named DELF for recommendation with implicit feedback. In addition to learning a single embedding for a user (resp. item), we represent each user (resp. item) with an additional embedding from the perspective of the interacted items (resp. users). We employ an attentive neural method to discriminate the importance of interacted users/items for dual-embedding learning. We further introduce a neural network architecture to incorporate dual embeddings for recommendation. A novel attempt of DELF is to model each user-item interaction with four deep representations that are subtly fused for preference prediction. We conducted extensive experiments on real-world datasets. The results verify the effectiveness of user/item dual embeddings and the superior performance of DELF on item recommendation.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

Differentiable Neural Input Search for Recommender Systems (2020, background): “Prior works have developed various architectures for G, including the simple inner product function [36], and deep neural networks-based interaction functions [6, 8, 16, 19, 24].”
Incorporating Interpretability into Latent Factor Models via Fast Influence Analysis (2018, unknown): “Wang et al. (2018) and Cheng et al. (2018b) empowered LFMs with explanations using both product features and review aspects.”
Where to Go Next: Modeling Long- and Short-Term User Preferences for Point-of-Interest Recommendation (2020, background): “POI recommendation is of high value to both the users and service providers, and has thus attracted much attention from researchers in the recent years (Yin et al. 2016; Cheng et al. 2018; Zhao et al. 2019).”
Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems (2019, methodology): “rformance of our DANSER. „e optimal hyper-parameter se−ings for each method are determined either by our experiments or suggested by previous works. „e recommendation models include SVD++[15] and DELF[2]. „ese two methods only leverage user-item interactions as model input. „eycanbeusedtoevaluatethe”
Jointly Learning Explainable Rules for Recommendation with Knowledge Graph (2019, methodology): “Following previous studies [5, 13],MLP and GMF are taken as baseline models too.”