Vzorčenje soseščine v heterogenih grafih pri grafovskih nevronskih mrežah : magistrsko delo

Keršič, Vid

| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

First page > Show document

Show document

Title:	Vzorčenje soseščine v heterogenih grafih pri grafovskih nevronskih mrežah : magistrsko delo
Authors:	ID Keršič, Vid (Author) ID Strnad, Damjan (Mentor) More about this mentor...
Files:	MAG_Kersic_Vid_2022.pdf (1,59 MB) MD5: D475A80D2E7CFE335A4331354B1CEEBB
Language:	Slovenian
Work type:	Master's thesis/paper
Typology:	2.09 - Master's Thesis
Organization:	FERI - Faculty of Electrical Engineering and Computer Science
Abstract:	Grafovske nevronske mreže so v zadnjem času eno izmed najbolj aktivnih področij raziskovanja globokega učenja. Uspešno so bile uporabljene pri problemih, kjer so podatki predstavljeni v obliki grafa, na primer pri analizi družbenih omrežij, napovedovanju prometa, razvoju zdravil itd. Kljub nekaterim zelo dobrim rezultatom pa ostaja še veliko odprtih izzivov pri uporabi nevronskih mrež na zelo velikih grafih, kjer smo omejeni z zmogljivostjo strojne opreme. V magistrskem delu naslavljamo problem uporabe grafovskih nevronskih mrež na obsežnih heterogenih grafih, kjer se med učenjem izvaja vzorčenje soseščine na vsaki plasti mreže, pri čemer se velikosti vzorca omejijo s hiperparametri. Heterogeni grafi vsebujejo več različnih tipov vozlišč in povezav, kar je pri vzorčenju soseščine koristno upoštevati in optimizirati vrednosti hiperparametrov za posamezne tipe povezav. Za reševanje tega problema predstavimo in analiziramo lasten algoritem, ki odpravi potrebo po časovno zahtevnem procesu obravnavanja in nastavljanja hiperparametrov za vse tipe vozlišč ter povezav. Prednosti algoritma z vidika časovne zahtevnosti in uspešnosti klasifikacije prikažemo na dveh grafih – akademskem grafu MAG240M, ki vsebuje več kot 240 milijonov vozlišč in nekaj manj kot 2 milijardi povezav, ter grafu znanja Freebase.
Keywords:	umetna inteligenca, strojno učenje, heterogeni grafi, grafovske nevronske mreže
Place of publishing:	Maribor
Place of performance:	Maribor
Publisher:	[V. Keršič]
Year of publishing:	2022
Number of pages:	1 spletni vir (1 datoteka PDF (XI, 51 f.))
PID:	20.500.12556/DKUM-82465
UDC:	004.8:004.032.26(043.2)
COBISS.SI-ID:	130211587
Publication date in DKUM:	20.10.2022
Views:	816
Downloads:	103
Metadata:
Categories:	KTFMB - FERI
:	Copy citation

Average score:	(0 votes)
Your score:	Voting is allowed only for logged in users.
Share:

Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:	CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International

Link:	http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:	The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:	22.08.2022

Secondary language

Language:	English
Title:	Neighborhood sampling of heterogeneous graphs in graph neural networks
Abstract:	In the last few years, graph neural networks have become one of the most active research fields in deep learning. They have been successfully applied for different problems, which can be represented as graphs, such as analysis of social networks, traffic prediction, and drug development. Despite the many successful results, there are still several challenges that need to be addressed when applying graph neural networks to large graphs, where there are hardware limitations. In the master's thesis, we tackle the problem of using graph neural networks on massive heterogeneous graphs, where neighborhood sampling is performed on each layer of the graph neural network, whereas the hyperparameters define the sample size. Heterogeneous graphs contain many node and edge types, which should be considered during the neighborhood sampling for more effective learning and optimized during hyperparameter tuning. For this purpose, we design and analyze the algorithm to remove the need for the time-consuming process of setting all the hyperparameters for all edge types. The algorithm's advantages are presented from the perspective of time complexity and classification efficiency on two graphs – the academic graph MAG240M, which contains more than 240 million nodes and a little less than 2 billion edges, and the knowledge graph Freebase.
Keywords:	artificial intelligence, machine learning, heterogeneous graphs, graph neural networks

Comments

Leave comment

You must log in to leave a comment.

Comments (0)

0 - 0 / 0

There are no comments!

Back