0% Complete
English
صفحه اصلی
/
یازدهمین کنفرانس بین المللی فناوری اطلاعات و دانش
Improving hypergraph attention and hypergraph convolution networks
نویسندگان :
Mustafa Mohammadi Gharasuie
1
Mahmood Shabankhah
2
Ali Kamandi
3
1- دانشگاه تهران
2- دانشگاه تهران
3- ٔدانشگاه تهران
کلمات کلیدی :
Graph Attention Network (GAT), Graph Convolutional Network (GCN), Hypergraph Attention Network (HAN), Hypergraph Convolutional Network (HGCN). a
چکیده :
Graph Neural Networks (GNNs) are models that use the structure of graphs to better exploit the bilateral relationship between neighboring nodes. Some problems, however, require that we consider a more general relationship which involve not only two nodes but rather a group of nodes. This is the approach adopted in Hypergraph Convolution and Hypergraph Attention Networks (HGAN) [1]. In this paper, we first propose to incorporate a weight matrix into these networks which, as our experimentations show, can improve the performance of the models in question. The other novelty in our work is the introduction of self-loops in the graphs which again leads to slight improvements in the accuracy of HAN. Index Terms—Graph Attention Network (GAT), Graph Convolutional Network (GCN), Hypergraph Attention Network (HAN), Hypergraph Convolutional Network (HGCN).
لیست مقالات
لیست مقالات بایگانی شده
An Enhanced Fuzzy Rule-Based Method for Coronary Artery Disease Risk Prediction Using Weighted and Biased Rules
Fatemeh Ahmadi - Mohammad Javad Parseh - Ehsan Amiri
روشی برای تشخیص مرحله پیشرفت آلزایمر در تصاویرFMRI مبتنی بر شبکه های عصبی چگال
فرساد زمانی بروجنی - عباس بهره دار
Combinatorial Auction Based on Social Choice in the Internet of Things
Maede Esmaeili - Faria Nassiri-Mofakham - Fatemeh Hassanvand
یک روش خوشه بندی گره ها برای شبکه های حسگر بیسیم با هدف بهبود متوازن سازی بار مبتنی بر تکنیک تاپسیس
راضیه حسین رضایی - فهیمه یزدان پناه
A Neural-based Approach to Aid Early Parkinson's Disease Diagnosis
Dr Armin Salimi-badr - Mohammad Hashemi
Prompt-Based Composed Fashion Image Retrieval via Gated Detail-Enhanced Dual Cross-Attention Difference Modeling
Kosar Keshavarz - Reza Azmi
A perceptual loss for screen content image super-resolution
Hossein Sekhavaty-Moghadam - Marzieh Hosseinkhani - Dr Azadeh Mansouri
Architectural Insights: Comparing Weight Stationary and Output Stationary Systolic Arrays for Efficient Computation
Mahdi Kalbasi
An efficient hybrid approach for performance-based alternative design evaluation in systems engineering
Abbas Chaman Para - Maryam Nooraei Abadeh - Sondos Bahadori
هوشمندسازی پایش کیفیت رنگزنی داخلی گرین تایر و تحلیل داده برای بهینه سازی عمر بلادر، مصرف رنگ و ریشه یابی عیوب پخت
سامان ثنایی - رضا رحیمی
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.5.2