Filters








4,550 Hits in 5.1 sec

Leveraging Two Types of Global Graph for Sequential Fashion Recommendation [article]

Yujuan Ding, Yunshan Ma, Wai Keung Wong, Tat-Seng Chua
2021 arXiv   pre-print
To tackle these problems, we propose to leverage two types of global graph, i.e., the user-item interaction graph and item-item transition graph, to obtain enhanced user and item representations by incorporating  ...  The key to building an effective sequential fashion recommendation model lies in capturing two types of patterns: the personal fashion preference of users and the transitional relationships between adjacent  ...  To the best of our knowledge [32] , this is the first work to leverage both u-i and i-i global graphs for sequential fashion recommendation. • We propose a new design for the i-i transition graph construction  ... 
arXiv:2105.07585v2 fatcat:kw7bwculbbfqtm3nyn2kmovin4

Beyond Clicks: Modeling Multi-Relational Item Graph for Session-Based Target Behavior Prediction [article]

Wen Wang, Wei Zhang, Shukai Liu, Qi Liu, Bo Zhang, Leyu Lin, Hongyuan Zha
2021 arXiv   pre-print
The extensive experiments on two real-world datasets demonstrate the superiority of MGNN-SPred by comparing with state-of-the-art session-based prediction methods, validating the benefits of leveraging  ...  Firstly, they focus on only utilizing the same type of user behavior for prediction, but ignore the potential of taking other behavior data as auxiliary information.  ...  Heterogeneous graph neural network [32] is applied for recommendation, with two edge types and one node type.  ... 
arXiv:2002.07993v3 fatcat:q4tzfeo7rfezjihvnwq66fv35e

A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation [article]

Le Wu, Xiangnan He, Xiang Wang, Kun Zhang, Meng Wang
2021 arXiv   pre-print
After reviewing representative work for each type, we finally discuss some promising directions in this field.  ...  ; and 3) temporal/sequential recommendation, which accounts for the contextual information associated with an interaction, such as time, location, and the past interactions.  ...  To this end, researchers argued that it is better to leverage the GNN based models to better model the global social diffusion process for recommendation.  ... 
arXiv:2104.13030v3 fatcat:7bzwaxcarrgbhe36teik2rhl6e

Research Commentary on Recommendations with Side Information: A Survey and Research Directions [article]

Zhu Sun, Qing Guo, Jie Yang, Hui Fang, Guibing Guo, Jie Zhang, Robin Burke
2019 arXiv   pre-print
Specifically, we provide an overview of state-of-the-art recommendation algorithms with side information from two orthogonal perspectives.  ...  To address these issues, a great number of recommendation algorithms have been proposed to leverage side information of users or items (e.g., social network and item category), demonstrating a high degree  ...  We also gratefully acknowledge the support of National Natural Science Foundation of China (Grant No. 71601104, 71601116, 71771141 and 61702084) and the support of the Fundamental Research Funds for the  ... 
arXiv:1909.12807v2 fatcat:2nj4crzcd5attidhd3kneszmki

Survey for Trust-aware Recommender Systems: A Deep Learning Perspective [article]

Manqing Dong, Feng Yuan, Lina Yao, Xianzhi Wang, Xiwei Xu, Liming Zhu
2020 arXiv   pre-print
A significant remaining challenge for existing recommender systems is that users may not trust the recommender systems for either lack of explanation or inaccurate recommendation results.  ...  This survey provides a systemic summary of three categories of trust-aware recommender systems: social-aware recommender systems that leverage users' social relationships; robust recommender systems that  ...  Shown in figure 16 , MANN can capture two different types of sequential patterns.  ... 
arXiv:2004.03774v2 fatcat:q7mehir7hbbzpemw3q5fkby5ty

A Survey on Knowledge Graph-Based Recommender Systems [article]

Qingyu Guo, Fuzhen Zhuang, Chuan Qin, Hengshu Zhu, Xing Xie, Hui Xiong, Qing He
2020 arXiv   pre-print
In this paper, we conduct a systematical survey of knowledge graph-based recommender systems. We collect recently published papers in this field and summarize them from two perspectives.  ...  On the one hand, we investigate the proposed algorithms by focusing on how the papers utilize the knowledge graph for accurate and explainable recommendation.  ...  [44] proposed the KSR framework for sequential recommendation.  ... 
arXiv:2003.00911v1 fatcat:qhyca7pu3beqtk6x55kpggowea

On Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observability (Extended Abstract)

Vincent Francois-Lavet, Guillaume Rabusseau, Joelle Pineau, Damien Ernst, Raphael Fonteneau
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
In the context of reinforcement learning with partial observability, this paper provides an analysis of the tradeoff between these two error sources.  ...  When an agent has limited information on its environment, the suboptimality of an RL algorithm can be decomposed into the sum of two terms: a term related to an asymptotic bias (suboptimality with unlimited  ...  There are mainly two types of factorization methods, which require different inputs for model training.  ... 
doi:10.24963/ijcai.2020/695 dblp:conf/ijcai/0001Z20 fatcat:yx2wihhuobgmjjh4aevkbr33g4

Controllable Multi-Interest Framework for Recommendation [article]

Yukuo Cen, Jianwei Zhang, Xu Zou, Chang Zhou, Hongxia Yang, Jie Tang
2020 arXiv   pre-print
We conduct experiments for the sequential recommendation on two real-world datasets, Amazon and Taobao.  ...  In this paper, we propose a novel controllable multi-interest framework for the sequential recommendation, called ComiRec.  ...  ACKNOWLEDGMENTS The work is supported by the NSFC for Distinguished Young Scholar (61825602), NSFC (61836013), and a research fund supported by Alibaba Group.  ... 
arXiv:2005.09347v2 fatcat:wn5qjqh2ordfxcsxpemtzcjbsa

A Trio Neural Model for Dynamic Entity Relatedness Ranking

Tu Nguyen, Tuan Tran, Wolfgang Nejdl
2018 Proceedings of the 22nd Conference on Computational Natural Language Learning  
In this work, we propose a neural networkbased approach for dynamic entity relatedness, leveraging the collective attention as supervision.  ...  Our model is capable of learning rich and different entity representations in a joint framework.  ...  We thank the reviewers for the suggestions on the content and structure of the paper.  ... 
doi:10.18653/v1/k18-1004 dblp:conf/conll/NguyenTN18 fatcat:liasz2zhpnbnjmqh5dculu4lfa

Deep Learning for Sequential Recommendation: Algorithms, Influential Factors, and Evaluations [article]

Hui Fang, Danning Zhang, Yiheng Shu, Guibing Guo
2020 arXiv   pre-print
Specifically,we illustrate the concept of sequential recommendation, propose a categorization of existing algorithms in terms of three types of behavioral sequence, summarize the key factors affecting  ...  However, there is little systematic study on DL-based methods, especially regarding to how to design an effective DL model for sequential recommendation.  ...  For example, Huang et al. [40] leveraged knowledge graph for better explanability in the sequential recommendation.  ... 
arXiv:1905.01997v3 fatcat:i7hvdiqjpnaupcq2osrblttb4u

Factorbird - a Parameter Server Approach to Distributed Matrix Factorization [article]

Sebastian Schelter, Venu Satuluri, Reza Zadeh
2014 arXiv   pre-print
We also discuss other aspects of the design of our system such as how to efficiently grid search for hyperparameters at scale.  ...  We present experiments of Factorbird on a matrix built from a subset of Twitter's interaction graph, consisting of more than 38 billion non-zeros and about 200 million rows and columns, which is to the  ...  In this work, we describe 'Factorbird', a prototypical system that leverages a parameter server architecture [17] for learning large matrix factorization models for recommendation mining.  ... 
arXiv:1411.0602v1 fatcat:mn6xwse2afg65m2hzkyfi5ezye

Multi-Task Learning of Graph-based Inductive Representations of Music Content

Antonia Saravanou, Federico Tomasi, Rishabh Mehrotra, Mounia Lalmas
2021 Zenodo  
We advocate for a multi-task formulation of graph representation learning, and propose MUSIG: Multi-task Sampling and Inductive learning on Graphs.  ...  We present large scale empirical results for track recommendation for the playlist completion task, and compare different classes of representation learning approaches, including collaborative filtering  ...  When learning track representations, one can leverage various types of heterogeneous information encoded in music data to benefit downstream tasks of music recommendation: (i) organizational information  ... 
doi:10.5281/zenodo.5624379 fatcat:ieavs4dz45aovk5w36voncrbfu

NUMA-aware graph-structured analytics

Kaiyuan Zhang, Rong Chen, Haibo Chen
2015 Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming - PPoPP 2015  
Our study uncovers two insights: 1) either random or interleaved allocation of graph data will significantly hamper data locality and parallelism; 2) sequential inter-node (i.e., remote) memory accesses  ...  Graph-structured analytics has been widely adopted in a number of big data applications such as social computation, web-search and recommendation systems.  ...  Acknowledgments We thank the anonymous reviewers for their insightful comments. This work is supported in part by the Doctoral  ... 
doi:10.1145/2688500.2688507 dblp:conf/ppopp/ZhangCC15 fatcat:rggubw77vzcxtnr3x5gab2rybu

NUMA-aware graph-structured analytics

Kaiyuan Zhang, Rong Chen, Haibo Chen
2015 SIGPLAN notices  
Our study uncovers two insights: 1) either random or interleaved allocation of graph data will significantly hamper data locality and parallelism; 2) sequential inter-node (i.e., remote) memory accesses  ...  Graph-structured analytics has been widely adopted in a number of big data applications such as social computation, web-search and recommendation systems.  ...  Acknowledgments We thank the anonymous reviewers for their insightful comments. This work is supported in part by the Doctoral  ... 
doi:10.1145/2858788.2688507 fatcat:zrmfubsbmfemldrnacuiup2oyu

Find Objects and Focus on Highlights: Mining Object Semantics for Video Highlight Detection via Graph Neural Networks

Yingying Zhang, Junyu Gao, Xiaoshan Yang, Chang Liu, Yan Li, Changsheng Xu
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
To reduce computational cost, we decompose the whole graph into two types of graphs: a spatial graph to capture the complex interactions of object within each frame, and a temporal graph to obtain object-aware  ...  representation of each frame and capture the global information.  ...  In this work, we build a object-aware graph and decompose the whole graph into two types of graphs, a spatial graph to capture the object semantics and a temporal graph to model the global information.  ... 
doi:10.1609/aaai.v34i07.6988 fatcat:biaanlopgvbw3nbt44niavse2m
« Previous Showing results 1 — 15 out of 4,550 results