Filters








37,455 Hits in 4.4 sec

Reinforced Negative Sampling over Knowledge Graph for Recommendation [article]

Xiang Wang, Yaokun Xu, Xiangnan He, Yixin Cao, Meng Wang, Tat-Seng Chua
2020 pre-print
Towards this end, we develop a new negative sampling model, Knowledge Graph Policy Network (KGPolicy), which works as a reinforcement learning agent to explore high-quality negatives.  ...  In this work, we hypothesize that item knowledge graph (KG), which provides rich relations among items and KG entities, could be useful to infer informative and factual negative samples.  ...  Towards this end, we propose a new negative sampling model, KGPolicy (short for Knowledge Graph Policy Network), which employs a reinforcement learning (RL) agent to explore KG to discover high-quality  ... 
doi:10.1145/3366423.3380098 arXiv:2003.05753v1 fatcat:csmmg25r7jbwxophuvjln6zt6y

Knowledge Graph-enhanced Sampling for Conversational Recommender System [article]

Mengyuan Zhao, Xiaowen Huang, Lixi Zhu, Jitao Sang, Jian Yu
2021 arXiv   pre-print
Then, two samplers are designed to enhance knowledge by sampling fuzzy samples with high uncertainty for obtaining user preferences and reliable negative samples for updating recommender to achieve efficient  ...  To address the aforementioned issue, this work proposes a contextual information enhancement model tailored for CRS, called Knowledge Graph-enhanced Sampling (KGenSam).  ...  item sample nodes in the KG, outputs high-quality negative samples through reinforcement learning, supplements sparse online user data with negative samples, and updates the recommender with positive  ... 
arXiv:2110.06637v1 fatcat:2e2uez3zynf2dbeeipvnqhtxza

A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions [article]

Xiaocong Chen, Lina Yao, Julian McAuley, Guanglin Zhou, Xianzhi Wang
2021 arXiv   pre-print
of the recent trends of deep reinforcement learning in recommender systems.  ...  In light of the emergence of deep reinforcement learning (DRL) in recommender systems research and several fruitful results in recent years, this survey aims to provide a timely and comprehensive overview  ...  [98] propose a method named Knowledge-guided Reinforcement Learning (KERL), which integrates knowledge graphs into the REINFORCE algorithm.  ... 
arXiv:2109.03540v2 fatcat:5gwrbfcj3rc7jfkd54eseck5ga

A Survey on Reinforcement Learning for Recommender Systems [article]

Yuanguo Lin, Yong Liu, Fan Lin, Lixin Zou, Pengcheng Wu, Wenhua Zeng, Huanhuan Chen, Chunyan Miao
2022 arXiv   pre-print
In particular, Reinforcement Learning (RL) based recommender systems have become an emerging research topic in recent years.  ...  To understand the challenges and relevant solutions, there should be a reference for researchers and practitioners working on RL-based recommender systems.  ...  To discover informative negative feedback from the missing data, [92] proposes a KG policy network for knowledge-aware negative sampling, which employs an RL agent to search high-quality negative instances  ... 
arXiv:2109.10665v2 fatcat:wx5ghn66hzg7faxee54jf7gspq

Reinforcement Learning based Path Exploration for Sequential Explainable Recommendation [article]

Yicong Li, Hongxu Chen, Yile Li, Lin Li, Philip S. Yu, Guandong Xu
2021 arXiv   pre-print
items with attention mechanisms to sequentially model dynamic user-item evolutions on dynamic knowledge graph for explainable recommendation.  ...  Recent advances in path-based explainable recommendation systems have attracted increasing attention thanks to the rich information provided by knowledge graphs.  ...  INTRODUCTION Reasoning with paths over user-item associated Knowledge Graphs (KGs) has been becoming a popular means for explainable recommendations [1] , [2] , [3] .  ... 
arXiv:2111.12262v1 fatcat:rcgzx3akvjamjjvj4zvy6kptle

Understanding Negative Sampling in Knowledge Graph Embedding

Jing Qian, Gangmin Li, Katie Atkinson, Yong Yue
2021 International Journal of Artificial Intelligence & Applications  
The quality of generated negative samples has a direct impact on the performance of learnt knowledge representation in a myriad of downstream tasks, such as recommendation, link prediction and node classification  ...  Most KGs store only positive samples for space efficiency. Negative sampling thus plays a crucial role in encoding triples of a KG.  ...  CONCLUSIVE REMARKS In this paper we have reviewed negative sampling in knowledge graph embedding.  ... 
doi:10.5121/ijaia.2021.12105 fatcat:djli7s2i6ndstjh6zav5mojhdy

CoSam: An Efficient Collaborative Adaptive Sampler for Recommendation [article]

Jiawei Chen, Chengquan Jiang, Can Wang, Sheng Zhou, Yan Feng, Chun Chen, Martin Ester, Xiangnan He
2020 arXiv   pre-print
A promising solution for this problem is to over-sample the "difficult" (a.k.a informative) instances that contribute more on training.  ...  Correspondingly, we derive a fast reinforced training algorithm of our framework to boost the sampler performance and sampler-recommender collaboration.  ...  [39] leverages knowledge graph to enhance negative sampling. However, these auxiliary information may not be available in many recommendation systems. Random walk in recommendation.  ... 
arXiv:2011.07739v1 fatcat:wktdowkk7be2dnou63g2pzoslq

[Paper] Deep Reinforcement Learning-based Music Recommendation with Knowledge Graph Using Acoustic Features

Keigo Sakurai, Ren Togo, Takahiro Ogawa, Miki Haseyama
2022 ITE Transactions on Media Technology and Applications  
In this study, we propose a new deep reinforcement learning-based music recommendation method with knowledge graphs.  ...  Furthermore, we realize efficient search using a deep reinforcement learning algorithm on a dense knowledge graph introducing acoustic feature-based edges.  ...  Zhou et al . leveraged a prior knowledge in a knowledge graph to achieve high sample efficiency in a reinforcement learning-based interactive recommendation system [33] .  ... 
doi:10.3169/mta.10.8 fatcat:6lglumewgrex7pmvgblfdlbtcu

Online POI Recommendation: Learning Dynamic Geo-Human Interactions in Streams [article]

Dongjie Wang, Kunpeng Liu, Hui Xiong, Yanjie Fu
2022 arXiv   pre-print
In this paper, we focus on the problem of modeling dynamic geo-human interactions in streams for online POI recommendations.  ...  Specifically, we model a mixed-user event stream by unifying all users, visits, and geospatial contexts as a dynamic knowledge graph stream, in order to model human-human, geo-human, geo-geo interactions  ...  Knowledge Graph-based Recommendation. Knowledge graph (KG) demonstrates the semantic relations and reasoning structure among different entities.  ... 
arXiv:2201.10983v1 fatcat:2fysztm4mfba7nugsibghmi5km

Alleviating Cold-Start Problems in Recommendation through Pseudo-Labelling over Knowledge Graph [article]

Riku Togashi, Mayu Otani, Shin'ichi Satoh
2020 arXiv   pre-print
We propose a knowledge graph (KG)-aware recommender based on graph neural networks, which augments labelled samples through pseudo-labelling.  ...  Most present works leverage unobserved samples for extracting negative signals.  ...  Sampling Based on Knowledge Graph and Popularity 3.4.1 KG-Aware Item Sampling for Pseudo-Labelling.  ... 
arXiv:2011.05061v1 fatcat:3xelswj5zrfq5n72ozydj3dxuq

Neural-Symbolic Reasoning over Knowledge Graph for Multi-stage Explainable Recommendation [article]

Yikun Xian, Zuohui Fu, Qiaoying Huang, S. Muthukrishnan, Yongfeng Zhang
2020 arXiv   pre-print
Moreover, direct reasoning over large-scale knowledge graph can be costly due to the huge search space of pathfinding.  ...  from knowledge graph.  ...  Figure 1: A coarse-to-fine process of neural-symbolic reasoning over knowledge graph for explainable recommendation.  ... 
arXiv:2007.13207v1 fatcat:we2und23rvbghoprpjnzbgsxeu

KBGAN: Adversarial Learning for Knowledge Graph Embeddings [article]

Liwei Cai, William Yang Wang
2018 arXiv   pre-print
Because knowledge graphs typically only contain positive facts, sampling useful negative training examples is a non-trivial task.  ...  Inspired by generative adversarial networks (GANs), we use one knowledge graph embedding model as a negative sample generator to assist the training of our desired model, which acts as the discriminator  ...  Conclusions We propose a novel adversarial learning method for improving a wide range of knowledge graph embedding models-We designed a generatordiscriminator framework with dual KGE components.  ... 
arXiv:1711.04071v3 fatcat:3n52ch36evaivh4a2jt5olt65i

KBGAN: Adversarial Learning for Knowledge Graph Embeddings

Liwei Cai, William Yang Wang
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)  
Because knowledge graphs typically only contain positive facts, sampling useful negative training examples is a nontrivial task.  ...  Inspired by generative adversarial networks (GANs), we use one knowledge graph embedding model as a negative sample generator to assist the training of our desired model, which acts as the discriminator  ...  Conclusions We propose a novel adversarial learning method for improving a wide range of knowledge graph embedding models-We designed a generatordiscriminator framework with dual KGE components.  ... 
doi:10.18653/v1/n18-1133 dblp:conf/naacl/CaiW18 fatcat:yecuzmprl5eyvmfzvfnsaln5yu

Knowledge-guided Deep Reinforcement Learning for Interactive Recommendation

Xiaocong Chen, Chaoran Huang, Lina Yao, Xianzhi Wang, Wei liu, Wenjie Zhang
2020 2020 International Joint Conference on Neural Networks (IJCNN)  
both reinforcement learning and knowledge graphs for the interactive recommendation.  ...  Inspired by the recent advance in Graph Convolutional Network and the knowledge-aware recommendation, we design a Knowledge-Guided deep Reinforcement learning (KGRL) model to harness the advantages of  ...  both reinforcement learning and knowledge graphs for the interactive recommendation.  ... 
doi:10.1109/ijcnn48605.2020.9207010 dblp:conf/ijcnn/Chen0Y00Z20 fatcat:3hlajcrneze4vbsnotyy475roa

Training like Playing: A Reinforcement Learning And Knowledge Graph-based framework for building Automatic Consultation System in Medical Field [article]

Yining Huang, Meilian Chen, Keke Tang
2021 arXiv   pre-print
We introduce a framework for AI-based medical consultation system with knowledge graph embedding and reinforcement learning components and its implement.  ...  Our implement of this framework leverages knowledge organized as a graph to have diagnosis according to evidence collected from patients recurrently and dynamically.  ...  Inspiration of reasoning over knowledge graph in consultation system can be drew from those works.  ... 
arXiv:2106.07502v1 fatcat:qwfzrhme6rfefe4idvk2do422y
« Previous Showing results 1 — 15 out of 37,455 results