paper-with-me

홈 › Papers

Graph Neural Networks for Image Classification and Reinforcement Learning using Graph representations

2022-03-07 · Naman Goyal, David Steiner

In this paper, we will evaluate the performance of graph neural networks in two distinct domains: computer vision and reinforcement learning. In the computer vision section, we seek to learn whether a novel non-redundant representation for images as graphs can improve performance over trivial pixel to node mapping on a graph-level prediction graph, specifically image classification. For the reinforcement learning section, we seek to learn if explicitly modeling solving a Rubik's cube as a graph problem can improve performance over a standard model-free technique with no inductive bias.

📄 PDF Abstract BibTeX arXiv:2203.03457

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage ClassificationInductive Biasreinforcement-learningReinforcement LearningReinforcement Learning (RL)Rubik's Cube

Similar Papers 제목 키워드 기반

SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanism

2021-01-20 · Qingyun Sun, JianXin Li, Hao Peng, Jia Wu 외

Graph representation learning has attracted increasing research attention. However, most existing studies fuse all structural features and node attributes to provide an overarching view of graphs, neglecting finer substr…

Graph ClassificationGraph Neural NetworkGraph Representation LearningRepresentation Learning

Collaborative Graph Walk for Semi-supervised Multi-Label Node Classification

2019-10-22 · Uchenna Akujuobi, Han Yufei, Qiannan Zhang, Xiangliang Zhang

In this work, we study semi-supervised multi-label node classification problem in attributed graphs. Classic solutions to multi-label node classification follow two steps, first learn node embedding and then build a node…

ClassificationGeneral ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION+2

Attention over Scene Graphs: Indoor Scene Representations Toward CSAI Classification

2025-09-30 · Artur Barros, Carlos Caetano, João Macedo, Jefersson A. dos Santos 외 arxiv

Indoor scene classification is a critical task in computer vision, with wide-ranging applications that go from robotics to sensitive content analysis, such as child sexual abuse imagery (CSAI) classification. The problem…

Scene Classification

Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations

2019-02-22 · Marcelo Daniel Gutierrez Mallea, Peter Meltzer, Peter J. Bentley

Graph classification is a significant problem in many scientific domains. It addresses tasks such as the classification of proteins and chemical compounds into categories according to their functions, or chemical and str…

BenchmarkingClassificationGeneral ClassificationGraph Classification+1

Learning Robust Representations with Graph Denoising Policy Network

2019-10-04 · Lu Wang, Wenchao Yu, Wei Wang, Wei Cheng 외

Graph representation learning, aiming to learn low-dimensional representations which capture the geometric dependencies between nodes in the original graph, has gained increasing popularity in a variety of graph analysis…

DenoisingGraph Representation LearningLink PredictionNode Classification+2