paper-with-me

홈 › Papers

Hyperparameter-free and Explainable Whole Graph Embedding

2021-08-04 · Hao Wang, Yue Deng, Linyuan Lü, Guanrong Chen

Graphs can be used to describe complex systems. Recently, whole graph embedding (graph representation learning) can compress a graph into a compact lower-dimension vector while preserving intrinsic properties, earning much attention. However, most graph embedding methods have problems such as tedious parameter tuning or poor explanation. This paper presents a simple and hyperparameter-free whole graph embedding method based on the DHC (Degree, H-index, and Coreness) theorem and Shannon Entropy (E), abbreviated as DHC-E. The DHC-E can provide a trade-off between simplicity and quality for supervised classification learning tasks involving molecular, social, and brain networks. Moreover, it performs well in lower-dimensional graph visualization. Overall, the DHC-E is simple, hyperparameter-free, and explainable for whole graph embedding with promising potential for exploring graph classification and lower-dimensional graph visualization.

📄 PDF Abstract BibTeX arXiv:2108.02113

Code (1)

HW-HaoWang/DHC-E 공식 구현

Tasks

Graph ClassificationGraph EmbeddingGraph Representation LearningHyperparameter OptimizationRepresentation Learning

Similar Papers 제목 키워드 기반

TWIG: Towards pre-hoc Hyperparameter Optimisation and Cross-Graph Generalisation via Simulated KGE Models

2024-02-08 · Jeffrey Sardina, John D. Kelleher, Declan O'Sullivan

In this paper we introduce TWIG (Topologically-Weighted Intelligence Generation), a novel, embedding-free paradigm for simulating the output of KGEs that uses a tiny fraction of the parameters. TWIG learns weights from i…

Link Prediction

Explainable and Position-Aware Learning in Digital Pathology

2023-06-14 · Milan Aryal, Nasim Yahyasoltani

Encoding whole slide images (WSI) as graphs is well motivated since it makes it possible for the gigapixel resolution WSI to be represented in its entirety for the purpose of graph learning. To this end, WSIs can be brok…

Graph AttentionGraph ClassificationGraph LearningPosition+1

Assessing the Effects of Hyperparameters on Knowledge Graph Embedding Quality

2022-07-01 · Oliver Lloyd, Yi Liu, Tom Gaunt

Embedding knowledge graphs into low-dimensional spaces is a popular method for applying approaches, such as link prediction or node classification, to these databases. This embedding process is very costly in terms of bo…

Graph EmbeddingKnowledge Graph EmbeddingKnowledge GraphsLink Prediction+2

CPa-WAC: Constellation Partitioning-based Scalable Weighted Aggregation Composition for Knowledge Graph Embedding

2024-08-01 · International Joint Conference on Artificial Intelligence 2024 8 · S. Modak, Aakarsh Malhotra, Sarthak Malik, Anil Surisetty 외

Scalability and training time are crucial for any graph neural network model processing a knowledge graph (KG). While partitioning knowledge graphs helps reduce the training time, the prediction accuracy reduces signifca…

Graph EmbeddingGraph Neural NetworkKnowledge Graph CompletionKnowledge Graph Embedding+1

Bayesian Learning of Conditional Kernel Mean Embeddings for Automatic Likelihood-Free Inference

2019-03-03 · Kelvin Hsu, Fabio Ramos

In likelihood-free settings where likelihood evaluations are intractable, approximate Bayesian computation (ABC) addresses the formidable inference task to discover plausible parameters of simulation programs that explai…