Filters








1,895 Hits in 5.4 sec

Joint Item Recommendation and Attribute Inference: An Adaptive Graph Convolutional Network Approach [article]

Le Wu, Yonghui Yang, Kun Zhang, Richang Hong, Yanjie Fu, Meng Wang
2020 arXiv   pre-print
To this end, in this paper, we define these two tasks in an attributed user-item bipartite graph, and propose an Adaptive Graph Convolutional Network (AGCN) approach for joint item recommendation and attribute  ...  Therefore, item recommendation and attribute inference have become two main tasks in these platforms.  ...  To tackle this challenge, we propose an Adaptive Graph Convolutional Network (AGCN) for both item recommendation and attribute inference.  ... 
arXiv:2005.12021v1 fatcat:dkuv35w5mvd2rofjjmk747vgje

KGAnet: a knowledge graph attention network for enhancing natural language inference

Meina Song, Wen Zhao, E. HaiHong
2020 Neural computing & applications (Print)  
In this paper, we propose a novel joint training framework that consists of a modified graph attention network, called the knowledge graph attention network, and an NLI model.  ...  Natural language inference (NLI) is the basic task of many applications such as question answering and paraphrase recognition.  ...  Acknowledgements This work is supported by the National Natural Science Foundation of China (No. 61902034) and Engineering Research Center of Information Networks, Ministry of Education.  ... 
doi:10.1007/s00521-020-04851-5 fatcat:swgexhoqdjf5rbmwalvzbrtqqm

A Survey on Causal Inference [article]

Liuyi Yao, Zhixuan Chu, Sheng Li, Yaliang Li, Jing Gao, Aidong Zhang
2020 arXiv   pre-print
The plausible applications of these methods are also presented, including the applications in advertising, recommendation, medicine and so on.  ...  Nowadays, estimating causal effect from observational data has become an appealing research direction owing to the large amount of available data and low budget requirement, compared with randomized controlled  ...  Applying Graph Convolutional Networks into causal inference model is an approach to handle the network data [46] .  ... 
arXiv:2002.02770v1 fatcat:kcedeyseevb3doht4pop26rqvy

Semantic Representation and Inference for NLP [article]

Dongsheng Wang
2021 arXiv   pre-print
The state of the art for semantic representation and inference is deep learning, and particularly Recurrent Neural Networks (RNNs), Convolutional Neural Networks (CNNs), and transformer Self-Attention  ...  and extending inference learning.  ...  Acknowledgments This research is partially supported by QUARTZ (721321, EU H2020 MSCA-ITN) and DABAI (5153-00004A, Innovation Fund Denmark).  ... 
arXiv:2106.08117v1 fatcat:qi3546wlhfd2xhqj3f776wa6km

Cognitive-aware Short-text Understanding for Inferring Professions [article]

Sayna Esmailzadeh, Saeid Hosseini, Mohammad Reza Kangavari, Wen Hua
2021 arXiv   pre-print
To this end, we devise a novel framework that on the one hand, can infer short-text contents and exploit cognitive features, and on the other hand, fuses various adopted novel algorithms, such as curve  ...  Firstly brief textual contents come with excessive lexical noise that makes the inference problem challenging.  ...  To this end, we employ an adapted divide and expansion method to approximately estimate the actuation interims.  ... 
arXiv:2106.07363v1 fatcat:xvnovqo3dff5np7fg75rcz77ya

Recent Advances in Heterogeneous Relation Learning for Recommendation [article]

Chao Huang
2021 arXiv   pre-print
We discuss the learning approaches in each category, such as matrix factorization, attention mechanism and graph neural networks, for effectively distilling heterogeneous contextual information.  ...  To address this problem, recent research developments can fall into three major lines: social recommendation, knowledge graph-enhanced recommender system, and multi-behavior recommendation.  ...  (i) Graph Convolutional Network-based Models. Inspired General GNN Social Recommendation Framework.  ... 
arXiv:2110.03455v1 fatcat:fskj4qdsibfnxefklazdli3tgu

A Universal Model for Cross Modality Mapping by Relational Reasoning [article]

Zun Li, Congyan Lang, Liqian Liang, Tao Wang, Songhe Feng, Jun Wu, Yidong Li
2021 arXiv   pre-print
Motivated by this, we redefine the mapping function with relational reasoning via graph modeling, and further propose a GCN-based Relational Reasoning Network (RR-Net) in which inter and intra relations  ...  in previous approaches.  ...  Graph Neural Network Recently, graph neural networks [40] [41] [42] [43] [44] , especially the graph convolutional network (GCN), have realized obvious progress because of its expressive power in handing  ... 
arXiv:2102.13360v1 fatcat:ng7p7cgi2zfxjldpql37udtqca

A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning [article]

Di Jin, Zhizhi Yu, Pengfei Jiao, Shirui Pan, Dongxiao He, Jia Wu, Philip S. Yu, Weixiong Zhang
2021 arXiv   pre-print
Classical approaches to community detection typically utilize probabilistic graphical models and adopt a variety of prior knowledge to infer community structures.  ...  As the problems that network methods try to solve and the network data to be analyzed become increasingly more sophisticated, new approaches have also been proposed and developed, particularly those that  ...  and integrat-ing graph convolutional networks and undirected graphical models.  ... 
arXiv:2101.01669v3 fatcat:p2lkjuslmzd6hc6kpum3sz5xwq

Learning Set Functions Under the Optimal Subset Oracle via Equivariant Variational Inference [article]

Zijing Ou, Tingyang Xu, Qinliang Su, Yingzhen Li, Peilin Zhao, Yatao Bian
2022 arXiv   pre-print
The main components of our framework involve: an energy-based treatment of the set mass function, DeepSet-style architectures to handle permutation invariance, mean-field variational inference, and its  ...  Learning set functions becomes increasingly more important in many applications like product recommendation and compound selection in AI-aided drug discovery.  ...  The atomic convolutional network (ACNN) (Gomes et al., 2017) provides meaningful vector features for complexes by constructing nearest neighbor graphs based on the 3D coordinates of atoms and predicting  ... 
arXiv:2203.01693v1 fatcat:k73xaqn7obgx3lem2nq6ostavq

Graph Contextualized Self-Attention Network for Session-based Recommendation

Chengfeng Xu, Pengpeng Zhao, Yanchi Liu, Victor S. Sheng, Jiajie Xu, Fuzhen Zhuang, Junhua Fang, Xiaofang Zhou
2019 Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence  
In this paper, we propose a graph contextualized self-attention model (GC-SAN), which utilizes both graph neural network and self-attention mechanism, for session-based recommendation.  ...  In GC-SAN, we dynamically construct a graph structure for session sequences and capture rich local dependencies via graph neural network (GNN).  ...  A natural solution to this problem is the item-to-item recommendation approaches .  ... 
doi:10.24963/ijcai.2019/547 dblp:conf/ijcai/XuZLSXZFZ19 fatcat:ge2hv6gl4ffexokdrhhyzvccw4

Great Expectations: Unsupervised Inference of Suspense, Surprise and Salience in Storytelling [article]

David Wilmot
2022 arXiv   pre-print
much cheaper and more adaptable to other domains and tasks.  ...  Extensions add memory and external knowledge from story plots and from Wikipedia to infer salience on novels such as Great Expectations and plays such as Macbeth.  ...  Unlike QDGAT, rather than higher-level reasoning modules, these graphs are fed into a GNN (Graph Neural Network) that infers the answering directly and can provide higher-order graph-level vector representations  ... 
arXiv:2206.09708v1 fatcat:k4oefywyxvgn5gdtedyvr5mbpi

Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation [article]

Junliang Yu, Hongzhi Yin, Jundong Li, Qinyong Wang, Nguyen Quoc Viet Hung, Xiangliang Zhang
2022 arXiv   pre-print
In this paper, we fill this gap and propose a multi-channel hypergraph convolutional network to enhance social recommendation by leveraging high-order user relations.  ...  Social relations are often used to improve recommendation quality when user-item interaction data is sparse in recommender systems.  ...  DP190101985 and DP170103954). Jundong Li is supported by National Science Foundation (NSF) under grant No. 2006844.  ... 
arXiv:2101.06448v4 fatcat:dnjuxs7xgjaahod2qfetzj6fsa

MEGCF: Multimodal Entity Graph Collaborative Filtering for Personalized Recommendation

Kang Liu, Feng Xue, Dan Guo, Le Wu, Shujie Li, Richang Hong
2022 ACM Transactions on Information Systems  
Afterwards, a symmetric linear Graph Convolution Network (GCN) module is constructed to perform message propagation over the graph, in order to capture both high-order semantic correlation and collaborative  ...  These entities are then integrated into the user-item interaction graph.  ...  ACKNOWLEDGMENTS This work is supported in part by the Seventh Special Support Plan for Innovation and Entrepreneurship in Anhui Province and in part by the National Natural Science Foundation of China  ... 
doi:10.1145/3544106 fatcat:eoxqkvag4bg5nay4wnriqmwc6u

Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation

Junliang Yu, Hongzhi Yin, Jundong Li, Qinyong Wang, Nguyen Quoc Viet Hung, Xiangliang Zhang
2021 Proceedings of the Web Conference 2021  
In this paper, we fill this gap and propose a multi-channel hypergraph convolutional network to enhance social recommendation by leveraging high-order user relations.  ...  Social relations are often used to improve recommendation quality when user-item interaction data is sparse in recommender systems.  ...  DP190101985 and DP170103954). Jundong Li is supported by National Science Foundation (NSF) under grant No. 2006844.  ... 
doi:10.1145/3442381.3449844 fatcat:wmmkxp5rnzc6henb5lnmih7f4m

FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings

Cheng-Te Li, Cheng Hsu, Yang Zhang
2022 ACM Transactions on Intelligent Systems and Technology  
The aim of FPGE is two-fold: incorporating the knowledge of users' and items' attributes and their correlation into entity representations, and alleviating the unfair distributions of user attributes on  ...  One is to learn and distill personalized sequential features from the given user and her item sequence for SR. The other is fairness-aware preference graph embedding (FPGE).  ...  To robustly model the correlation between the current subsequence of items and the next items to be recommended, we propose a joint gating and convolutional subnetwork, which combines personalized feature  ... 
doi:10.1145/3495163 fatcat:jilgbb3rnbdx3jg3mk6olcpfwi
« Previous Showing results 1 — 15 out of 1,895 results