International Conference on Information and Knowledge Technology

فارسی

Home / یازدهمین کنفرانس بین المللی فناوری اطلاعات و دانش

Improving hypergraph attention and hypergraph convolution networks

Authors :

Mustafa Mohammadi Gharasuie¹ Mahmood Shabankhah² Ali Kamandi³

1- دانشگاه تهران 2- دانشگاه تهران 3- ٔدانشگاه تهران

Keywords :

Graph Attention Network (GAT), Graph Convolutional Network (GCN), Hypergraph Attention Network (HAN), Hypergraph Convolutional Network (HGCN). a

Abstract :

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).

List of archived papers

Identifying Children's Personality Styles through Drawing Analysis using Machine Learning

Maedeh Mosharraf - Faezeh Banabazi

قطعه بندی خودکار توده کلیه در تصاویر توموگرافی کامپیوتری با استفاده از هم‌افزایی شبکه عصبی عمیق U-Net و الگوریتم فراابتکاری نهنگ

علی خلیلی - محمد مصلح - محمد خیراندیش

A High-Speed Quantum Reversible Controlled Adder/Subtractor Circuit

Negin Mashayekhi - Mohammad Reza Reshadinezhad - Shekoofeh Moghimi

SecVanet: provably secure authentication protocol for sending emergency events in VANET

Seyed Amir Mousavi - Mohammad Sadeq Sirjani - Seyyed Javad Bozorg zadeh Razavi - Morteza Nikooghadam

بررسی روش یادگیری انتقالی جهت پیش‌بینی پیوند

علی روحانی فر - کمال میرزایی بدرآبادی

A Novel Resource Allocation Scheme for Underlaying NOMA-Based Multi-Channel Cognitive D2D Communications

Anahita Akbari - Dr Javad Zeraatkar Moghaddam - Dr Mehrdad Ardebilipour

A Mathematical Optimization Approach for Preference Learning in Movie Recommender Systems with Shared Accounts

Milad Khademali - Fazlollah Aghamohammadi - Marjan Kaedi - Alireza Nasiri

خوشه بندی ویسیلاب های دو آوایی زبان فارسی در کاربرد لب خوانی

مهسا هدایتی پور - دکتر یاسر شکفته - دکتر محسن ابراهیمی مقدم

Leveraging Retrieval-Augmented Generation for Persian University Knowledge Retrieval

Arshia Hemmat - Mohammad Hassan Heydari - Kianoosh Vadaei - Afsaneh Fatemi

Data Analysis to Reduce Electrical Power Plants

Amirali Sahraei - Jamshid Shanbehzadeh

more

Samin Hamayesh - Version 42.3.1