Feature Graph Architectures

2013-12-15 · Richard Davis, Sanjay Chawla, Philip Leong

In this article we propose feature graph architectures (FGA), which are deep learning systems employing a structured initialisation and training method based on a feature graph which facilitates improved generalisation performance compared with a standard shallow architecture. The goal is to explore alternative perspectives on the problem of deep network training. We evaluate FGA performance for deep SVMs on some experimental datasets, and show how generalisation and stability results may be derived for these models. We describe the effect of permutations on the model accuracy, and give a criterion for the optimal permutation in terms of feature correlations. The experimental results show that the algorithm produces robust and significant test set improvements over a standard shallow SVM training method for a range of datasets. These gains are achieved with a moderate increase in time complexity.

📄 PDF Abstract BibTeX arXiv:1312.4209

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SVM A Support Vector Machine, or SVM, is a non-parametric supervised learning model. For non-linear classification and regression, they utilise the kernel trick to map inputs…

Viewpoint Selection for Photographing Architectures

2017-03-06 · Jingwu He, Linbo Wang, Wenzhe Zhou, Hongjie Zhang 외

This paper studies the problem of how to choose good viewpoints for taking photographs of architectures. We achieve this by learning from professional photographs of world famous landmarks that are available on the Inter…

2k Clustering

On the Expressive Power of Spectral Invariant Graph Neural Networks

2024-06-06 · Bohang Zhang, Lingxiao Zhao, Haggai Maron

Incorporating spectral information to enhance Graph Neural Networks (GNNs) has shown promising results but raises a fundamental challenge due to the inherent ambiguity of eigenvectors. Various architectures have been pro…

A Sheaf-Theoretic and Topological Perspective on Complex Network Modeling and Attention Mechanisms in Graph Neural Models

2026-01-29 · Chuan-Shen Hu arxiv

Combinatorial and topological structures, such as graphs, simplicial complexes, and cell complexes, form the foundation of geometric and topological deep learning (GDL and TDL) architectures. These models aggregate signa…

Node Classification Community Detection

GLINKX: A Scalable Unified Framework For Homophilous and Heterophilous Graphs

2022-11-01 · Marios Papachristou, Rishab Goel, Frank Portman, Matthew Miller 외

In graph learning, there have been two predominant inductive biases regarding graph-inspired architectures: On the one hand, higher-order interactions and message passing work well on homophilous graphs and are leveraged…

Graph Learning Knowledge Graph Embeddings

Causal-aware Graph Neural Architecture Search under Distribution Shifts

2024-05-26 · Peiwen Li, Xin Wang, Zeyang Zhang, Yijian Qin 외

Graph NAS has emerged as a promising approach for autonomously designing GNN architectures by leveraging the correlations between graphs and architectures. Existing methods fail to generalize under distribution shifts th…

Graph Embedding Neural Architecture Search Out-of-Distribution Generalization