Proceedings Article10.1145/3394486.3403389
Hypergraph Convolutional Recurrent Neural Network
Jaehyuk Yi,Jinkyoo Park +1 more
- 23 Aug 2020
- pp 3366-3376
73
TL;DR: A hypergraph convolutional recurrent neural network (HGC-RNN), which is a prediction model for structured time-series sensor network data, using a hypergraph, which is capable of modeling complicated structures, for structural representation.
read more
Abstract: In this study, we present a hypergraph convolutional recurrent neural network (HGC-RNN), which is a prediction model for structured time-series sensor network data. Representing sensor networks in a graph structure is useful for expressing structural relationships among sensors. Conventional graph structure, however, has a limitation on representing complex structure in real world application, such as shared connections among multiple nodes. We use a hypergraph, which is capable of modeling complicated structures, for structural representation. HGC-RNN performs a hypergraph convolution operation on the input data represented in the hypergraph to extract hidden representations of the input, while considering the structural dependency of the data. HGC-RNN employs a recurrent neural network structure to learn temporal dependency from the data sequence. We conduct experiments to forecast taxi demand in NYC, traffic flow in the overhead hoist transfer system, and gas pressure in a gas regulator. We compare the performance of our method with those of other existing methods, and the result shows that HGC-RNN has strengths over baseline models.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A Survey on Hyperlink Prediction
Cang Chen,Yang-Yu Liu +1 more
TL;DR: A new taxonomy is proposed to classify existing hyperlink prediction methods into four categories: similarity- based, probability-based, matrix optimized, and deep learning-based methods.
Hypergraph Neural Networks for Time-series Forecasting
Hongjie Chen,Ryan A. Rossi,Kanak Mahadik,Sungchul Kim,Hoda Eldardiry +4 more
- 15 Dec 2023
TL;DR: A novel model called Hypergraph Recurrent Neural Networks (HGRNN) for time-series forecasting that employs a hypergraph to model beyond-pairwise relations, which naturally reflect the actual interactions among entities, and introduces a novel semi-principled hypergraph construction method to address the challenge of missing hypergraph information.
References
•Journal Article
Visualizing Data using t-SNE
TL;DR: A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.
XGBoost: A Scalable Tree Boosting System
Tianqi Chen,Carlos Guestrin +1 more
TL;DR: This paper proposes a novel sparsity-aware algorithm for sparse data and weighted quantile sketch for approximate tree learning and provides insights on cache access patterns, data compression and sharding to build a scalable tree boosting system called XGBoost.
•Posted Content
Semi-Supervised Classification with Graph Convolutional Networks
Thomas Kipf,Max Welling +1 more
TL;DR: A scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs which outperforms related methods by a significant margin.
22.7K
Graph Attention Networks
Petar Veličković,Guillem Cucurull,Arantxa Casanova,Adriana Romero,Pietro Liò,Yoshua Bengio +5 more
- 15 Feb 2018
TL;DR: Graph Attention Networks (GATs) as mentioned in this paper leverage masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations.
XGBoost: A Scalable Tree Boosting System
Tianqi Chen,Carlos Guestrin +1 more
- 13 Aug 2016
TL;DR: XGBoost as discussed by the authors proposes a sparsity-aware algorithm for sparse data and weighted quantile sketch for approximate tree learning to achieve state-of-the-art results on many machine learning challenges.