A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Filters
Aspect-Level Deep Collaborative Filtering via Heterogeneous Information Networks
2018
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Preserved Fulltext
Finally, the aspect-level latent factors are effectively fused with an attention mechanism for the top-N recommendation. ...
Latent factor models have been widely used for recommendation. ...
matrix (e.g., rating matrix) into two low-rank user-specific and item-specific factors, and then use the low-rank factors to make predictions. ...
doi:10.24963/ijcai.2018/471
dblp:conf/ijcai/HanSWYS18
fatcat:3y5bgcnbcbh25jk75v6vd2kkaq
Deep Collaborative Filtering with Multi-Aspect Information in Heterogeneous Networks
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
factor for users and items. ...
Latent factor models have been widely used for recommendation. ...
[32] propose the neural factorization machine (NFM) model for recommendation. ...
arXiv:1909.06627v1
fatcat:wqzcifktbfaqdg3cy7dwfnzxy4
DeepFusion: Fusing User-Generated Content and Item Raw Content towards Personalized Product Recommendation
2020
Complexity
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this framework, we utilize multiple types of deep neural networks that are best suited for each type of heterogeneous inputs and introduce an extra layer to obtain the joint representations for users ...
Personalized recommender systems, as effective approaches for alleviating information overload, have received substantial attention in the last decade. ...
(iii) DeepFusion-fm: we utilize the factorization machine [37] in place of the original neural prediction layer. ...
doi:10.1155/2020/4780191
fatcat:r5pixfcteze3hi46bdouxjnlp4
Identifying disease-associated circRNAs based on edge-weighted graph attention and heterogeneous graph neural network
[article]
2022
bioRxiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
graph neural networks for discovering probable circRNA-disease correlations prediction. ...
Using the revised node features, we learn meta-path contextual information and use heterogeneous neural networks to assign attention weights to different types of edges. ...
networks.applied neural networks to replace linear approximation based on matrix factorization for possible associations. ...
doi:10.1101/2022.05.04.490565
fatcat:tzuddw6ya5d3xh7xpsn6lsozuy
Learning Dynamic Factors to Improve the Accuracy of Bus Arrival Time Prediction via a Recurrent Neural Network
2019
Future Internet
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Experiments demonstrate that the prediction accuracy of RNN with an attention mechanism is better than RNN with no attention mechanism when there are heterogeneous input factors. ...
Previous studies have shown that to improve prediction accuracy, more heterogeneous measurements provide better results. So what other factors should be added into the prediction model? ...
And thanks Yong Wu provides the raw data for this paper.
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/fi11120247
fatcat:azghinr6wnhjrndqrdcmonh7ia
Deep Learning Model for House Price Prediction Using Heterogeneous Data Analysis Along With Joint Self-Attention Mechanism
2021
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
FIGURE 5 . 5 House price prediction based on a joint self-attention mechanism.
FIGURE 6 . 6 Weights generated by a gated neural network for house price prediction. ...
All models adopting the gated neural network for prediction outperform the models adopting only the center point as the house address. ...
doi:10.1109/access.2021.3071306
fatcat:qqcwboml4fgvjczusrgnjldac4
MTHetGNN: A Heterogeneous Graph Embedding Framework for Multivariate Time Series Forecasting
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Meanwhile, a temporal embedding module is introduced for time series features extraction, where involving convolutional neural network (CNN) filters with different perception scales. ...
In this paper, we propose a novel end-to-end deep learning model, termed Multivariate Time Series Forecasting via Heterogeneous Graph Neural Networks (MTHetGNN). ...
The heterogeneity and rich semantic information bring significant challenges for designing heterogeneous graph neural networks. ...
arXiv:2008.08617v4
fatcat:6mut5k4wkbhdpm66o4tjv6gyjm
Recent Advances in Heterogeneous Relation Learning for Recommendation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
We discuss the learning approaches in each category, such as matrix factorization, attention mechanism and graph neural networks, for effectively distilling heterogeneous contextual information. ...
Finally, we present an exploratory outlook to highlight several promising directions and opportunities in heterogeneous relational learning frameworks for recommendation. ...
Specifically, most of current approaches only focus on forecasting unknown user-item interactions, but ignore the inference of casual factors for predicted results. ...
arXiv:2110.03455v1
fatcat:fskj4qdsibfnxefklazdli3tgu
Granger-Causal Attentive Mixtures of Experts: Learning Important Features with Neural Networks
2019
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
AMEs use attentive gating networks trained with a Granger-causal objective to learn to jointly produce accurate predictions as well as estimates of feature importance in a single model. ...
Here, we present a new approach to estimating feature importance with neural networks based on the idea of distributing the features of interest among experts in an attentive mixture of experts (AME). ...
At prediction time, the attentive gating networks output an attention factor a i for each expert to control its respective contribution y i to the AMEs final prediction y. ...
doi:10.1609/aaai.v33i01.33014846
fatcat:l75oaelefrghjhpsjvux7amgvm
Connecting Latent ReLationships over Heterogeneous Attributed Network for Recommendation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Recently, deep neural network models for graph-structured data have been demonstrating to be influential in recommendation systems. ...
Furthermore, we propose a novel graph neural network-based model to deal with HAN for Recommendation, called HANRec. ...
Based on the nodes' latent factors in the graph, machine learning algorithms can complete downstream tasks more efficiently, such as recommendation tasks and link prediction tasks. ...
arXiv:2103.05749v1
fatcat:xii4gjvm6ren5e2rxroajmxr74
Feature Interaction-aware Graph Neural Networks
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper, we propose Feature Interaction-aware Graph Neural Networks (FI-GNNs), a plug-and-play GNN framework for learning node representations encoded with informative feature interactions. ...
Extensive experiments on various datasets demonstrate the superior capability of FI-GNNs for graph learning tasks. ...
Specifically, Neural Factorization Machines (NFMs) was proposed to enhance the expressive ability of standard FMs with nonlinear hidden layers for sparse predictive analytics. ...
arXiv:1908.07110v2
fatcat:fk76u5vxorfljom5s3ivwhk6ku
SGDAN—A Spatio-Temporal Graph Dual-Attention Neural Network for Quantified Flight Delay Prediction
2020
Sensors
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we develop a Spatio-temporal Graph Dual-Attention Neural Network (SGDAN) to learn the departure delay time for each flight with real-time conditions at three hours before the scheduled time ...
The main contributions of this paper are using heterogeneous graph-level attention to learn the influence between the flight and its adjacent flight together with sequence-level attention to learn the ...
, that is, Neural Network (NN), Support Vector Machines (SVM) and Random Forest (RF) to predict [5] . ...
doi:10.3390/s20226433
pmid:33187127
fatcat:i5yq6rbf7bezfoh27rdhmrjbom
A Heterogeneous Graph Enhanced LSTM Network for Hog Price Prediction Using Online Discussion
2021
Agriculture
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Such information has played an essential role in decision-making for farmers, consumers, corporations, and governments. It is hard to predict hog prices because too many factors can influence them. ...
To address these difficulties, we propose Heterogeneous Graph-enhanced LSTM (HGLTSM), which is a method that predicts weekly hog price. ...
For this time-series prediction task, researchers seek statistical methods and later machine learning methods. ...
doi:10.3390/agriculture11040359
fatcat:xkiihpp2tfdt3olib5yt5tbiyu
Graph Learning Approaches to Recommender Systems: A Review
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
With the rapid development of graph learning, exploring and exploiting homogeneous or heterogeneous relations in graphs is a promising direction for building advanced RS. ...
GLRS mainly employ the advanced graph learning approaches to model users' preferences and intentions as well as items' characteristics and popularity for Recommender Systems (RS). ...
Graph Factorization Machine based RS (GFMRS). ...
arXiv:2004.11718v1
fatcat:w6ug72c4pvgoxjcf643tmddfii
Gated Attentive-Autoencoder for Content-Aware Recommendation
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
To cope with these challenges, we propose a gated attentive-autoencoder (GATE) model, which is capable of learning fused hidden representations of items' contents and binary ratings, through a neural gating ...
The rapid growth of Internet services and mobile devices provides an excellent opportunity to satisfy the strong demand for the personalized item or product recommendation. ...
The yellow part is the stacked AE for binary rating prediction, and the green part is the word-attention module for item content. ...
arXiv:1812.02869v1
fatcat:yxisbveh7bcmxbgn4xy43qooiu
« Previous
Showing results 1 — 15 out of 24,235 results