OpenWGL: open-world graph learning for unseen class node classification

2021 ◽  
Author(s):  
Man Wu ◽  
Shirui Pan ◽  
Xingquan Zhu
Keyword(s):  
Graph Learning ◽  
Open World ◽  
Node Classification ◽  
Class Node

OpenWGL: Open-World Graph Learning

2020 ◽  
Author(s):  
Man Wu ◽  
Shirui Pan ◽  
Xingquan Zhu
Keyword(s):  
Graph Learning ◽  
Open World

scholarly journals Semisupervised Classification with High-Order Graph Learning Attention Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Wu-Lue Yang ◽  
Xiao-Ze Chen ◽  
Xu-Hua Yang
Keyword(s):  
Neural Network ◽  
High Order ◽  
Data Sets ◽  
Graph Structure ◽  
Graph Classification ◽  
Topological Graph ◽  
Data Set ◽  
Graph Learning ◽  
Semisupervised Classification ◽  
Node Classification

At present, the graph neural network has achieved good results in the semisupervised classification of graph structure data. However, the classification effect is greatly limited in those data without graph structure, incomplete graph structure, or noise. It has no high prediction accuracy and cannot solve the problem of the missing graph structure. Therefore, in this paper, we propose a high-order graph learning attention neural network (HGLAT) for semisupervised classification. First, a graph learning module based on the improved variational graph autoencoder is proposed, which can learn and optimize graph structures for data sets without topological graph structure and data sets with missing topological structure and perform regular constraints on the generated graph structure to make the optimized graph structure more reasonable. Then, in view of the shortcomings of graph attention neural network (GAT) that cannot make full use of the graph high-order topology structure for node classification and graph structure learning, we propose a graph classification module that extends the attention mechanism to high-order neighbors, in which attention decays according to the increase of neighbor order. HGLAT performs joint optimization on the two modules of graph learning and graph classification and performs semisupervised node classification while optimizing the graph structure, which improves the classification performance. On 5 real data sets, by comparing 8 classification methods, the experiment shows that HGLAT has achieved good classification results on both a data set with graph structure and a data set without graph structure.

scholarly journals Lifelong Learning of Graph Neural Networks for Open-World Node Classification

2021 ◽  
Author(s):  
Lukas Galke ◽  
Benedikt Franke ◽  
Tobias Zielke ◽  
Ansgar Scherp
Keyword(s):  
Neural Networks ◽  
Lifelong Learning ◽  
Open World ◽  
Node Classification ◽  
Graph Neural Networks

Open-World Virtual Reality Headset Tracking

2020 ◽  
Author(s):  
Todd E. Humphreys ◽  
Ronnie Xian Thong Kor ◽  
Peter A. Iannucci ◽  
James E. Yoder
Keyword(s):  
Virtual Reality ◽  
Open World

The Unified World Order

2014 ◽  
Vol 31 (2) ◽  
pp. 75-100
Author(s):  
Bakare Adewale Muteeu
Keyword(s):  
Cultural Values ◽  
International System ◽  
World Order ◽  
Social Injustice ◽  
World Peace ◽  
Technological Determinism ◽  
Open World ◽  
The World ◽  
Capitalist World ◽  
The Rich

In pursuit of a capitalist world configuration, the causal phenomenon of globalization spread its cultural values in the built international system, as evidenced by the dichotomy between the rich North and the poor South. This era of cultural globalization is predominantly characterized by social inequality, economic inequality and instability, political instability, social injustice, and environmental change. Consequently, the world is empirically infected by divergent global inequalities among nations and people, as evidenced by the numerous problems plaguing humanity. This article seeks to understand Islam from the viewpoint of technological determinism in attempt to offset these diverging global inequalities for its “sociopolitical economy”1existence, as well as the stabilization of the interconnected world. Based upon the unifying view of microIslamics, the meaning of Islam and its globalizing perspectives are deciphered on a built micro-religious platform. Finally, the world is rebuilt via the Open World Peace (OWP) paradigm, from which the fluidity of open globalization is derived as a future causal phenomenon for seamlessly bridging (or contracting) the gaps between the rich-rich, rich-poor, poor-rich and poor-poor nations and people based on common civilization fronts.

Island Generator pada Game Open world Menggunakan Algoritma Perlin noise

Repositor ◽  
2020 ◽  
Vol 2 (7) ◽  
pp. 965
Author(s):  
Naufal Azzmi ◽  
Lailatul Husniah ◽  
Ali Sofyan Kholimi
Keyword(s):  
Performance Testing ◽  
Game Development ◽  
Procedural Content Generation ◽  
Open World ◽  
Game World ◽  
Perlin Noise ◽  
And Performance ◽  
Game Developers ◽  
Pcg Method ◽  
Content Generation

AbstrakPerkembangan game pada saat ini berkembang dengan sangat cepat, dalam perkermbangan game topik AI adalah topik yang paling banyak diteliti oleh beberapa peneliti khususnya pada pembuatan suatu konten game menggunakan metode PCG (procedural content generation). Pada pembuatan sebuah game world menggunakan metode PCG sudah banyak developer game yang sukses dengan mengimplementasikan metode ini, metode ini banyak digunkan pada geme dengan genre RPG, Rouglikes, Platformer, SandBox, Simulation dan lain sebagainya, Pada penelitian ini berfokus pada pengembangan sebuah game world generator untuk game berjenis open world yang berupa sebuah kepulauan dengan metode PCG dengan menggunakan algoritma perlin noise sebagai algoritma pembentuk textur utama pulau yang dimana pada penelitian ini memanfaatkan beberapa variable noise seperti octave, presistance dan lacunarity guna untuk menambah kontrol dari hasil textur yang dihasilkan serta algoritma penempatan pulau untuk membuat sebuah game world yang menyerupai sebuah kepulauan. Dari hasil uji generator terkait degan pengujian playability dan performa dapat disimpulkan bahwa generator yang dikembangkan playable serta performa yang dianaliasa menggunakan notasi Big O menunjukkan  (linear). Abstract Game development is currently growing very fast, game development AI is the most discussed topic by most researchers especially in the developing of game content using the PCG (procedural content generation) method. In making a game world using the PCG method, many game developers have succeeded by implementing this method, this method is widely used on RPGs, Rouglikes, Platformers, SandBox, Simulations and ect,. This study focuses on developing a game world generator game for open world type games in the form of an archipelago using the PCG method using the noise perlin algorithm as the island's main texturizing algorithm which in this study utilizes several noise variables such as octave, presistance and use for add control of the texture results as well as the island placement algorithm’s to create a game world that resembles an archipelago form. From the generator test results related to the playability and performance testing, it shows that map are being generated by the generators are playable and performance that are analyzed using Big O notation show O (n) (linear).

Multi-view feature selection via Nonnegative Structured Graph Learning

2020 ◽  
Vol 387 ◽  
pp. 110-122 ◽  
Author(s):  
Xiangpin Bai ◽  
Lei Zhu ◽  
Cheng Liang ◽  
Jingjing Li ◽  
Xiushan Nie ◽  
...  
Keyword(s):  
Feature Selection ◽  
Graph Learning

scholarly journals Online Discriminative Graph Learning from Multi-Class Smooth Signals

2021 ◽  
pp. 108101
Author(s):  
Seyed Saman Saboksayr ◽  
Gonzalo Mateos ◽  
Mujdat Cetin
Keyword(s):  
Graph Learning
Sign in / Sign up

Export Citation Format

Share Document