F
Fajie Yuan
Researcher at Westlake University
Publications - 61
Citations - 1440
Fajie Yuan is an academic researcher from Westlake University. The author has contributed to research in topics: Recommender system & Computer science. The author has an hindex of 13, co-authored 51 publications receiving 841 citations. Previous affiliations of Fajie Yuan include Northeastern University (China) & Chinese Academy of Sciences.
Papers
More filters
Proceedings ArticleDOI
A Simple Convolutional Generative Network for Next Item Recommendation
TL;DR: In this paper, a generative model is proposed to learn high-level representation from both short and long-range item dependencies, which can be used as a powerful recommendation baseline to beat the current state-of-the-art.
Proceedings ArticleDOI
LambdaFM: Learning Optimal Ranking with Factorization Machines Using Lambda Surrogates
TL;DR: This paper introduces Lambda Factorization Machines (LambdaFM), which is particularly intended for optimizing ranking performance for IFCAR, and creates three effective lambda surrogates by conducting a theoretical analysis for lambda from the top-N optimization perspective.
Journal ArticleDOI
Adversarial Training Towards Robust Multimedia Recommender System
TL;DR: This paper proposes a novel solution named Adversarial Multimedia Recommendation (AMR), which can lead to a more robust multimedia recommender model by using adversarial learning, to train the model to defend an adversary, which adds perturbations to the target image with the purpose of decreasing the model's accuracy.
Posted Content
A Simple Convolutional Generative Network for Next Item Recommendation
TL;DR: A simple, but very effective generative model that is capable of learning high-level representation from both short- and long-range item dependencies is introduced that attains state-of-the-art accuracy with less training time in the next item recommendation task.
Proceedings ArticleDOI
Future Data Helps Training: Modeling Future Contexts for Session-based Recommendation
TL;DR: GRec as discussed by the authors proposes a gap-filling based recommender framework, where the encoder takes a partially-complete session sequence (where some items are masked by purpose) as input, and the decoder predicts these masked items conditioned on the encoded representation.