paper-with-me

홈 › Papers

Graph Embedding with Data Uncertainty

2020-09-01 · Firas Laakom, Jenni Raitoharju, Nikolaos Passalis, Alexandros Iosifidis, Moncef Gabbouj

spectral-based subspace learning is a common data preprocessing step in many machine learning pipelines. The main aim is to learn a meaningful low dimensional embedding of the data. However, most subspace learning methods do not take into consideration possible measurement inaccuracies or artifacts that can lead to data with high uncertainty. Thus, learning directly from raw data can be misleading and can negatively impact the accuracy. In this paper, we propose to model artifacts in training data using probability distributions; each data point is represented by a Gaussian distribution centered at the original data point and having a variance modeling its uncertainty. We reformulate the Graph Embedding framework to make it suitable for learning from distributions and we study as special cases the Linear Discriminant Analysis and the Marginal Fisher Analysis techniques. Furthermore, we propose two schemes for modeling data uncertainty based on pair-wise distances in an unsupervised and a supervised contexts.

📄 PDF Abstract BibTeX arXiv:2009.00505

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Embedding

Similar Papers 제목 키워드 기반

REGE: A Method for Incorporating Uncertainty in Graph Embeddings

2024-12-07 · Zohair Shafi, Germans Savcisens, Tina Eliassi-Rad

Machine learning models for graphs in real-world applications are prone to two primary types of uncertainty: (1) those that arise from incomplete and noisy data and (2) those that arise from uncertainty of the model in i…

DynG2G: An Efficient Stochastic Graph Embedding Method for Temporal Graphs

2021-09-28 · Mengjia Xu, Apoorva Vikram Singh, George Em Karniadakis

Dynamic graph embedding has gained great attention recently due to its capability of learning low dimensional graph representations for complex temporal graphs with high accuracy. However, recent advances mostly focus on…

DiversityDynamic graph embeddingGraph EmbeddingTriplet+1

Gaussian Embedding of Large-scale Attributed Graphs

2019-12-02 · Bhagya Hettige, Yuan-Fang Li, Weiqing Wang, Wray Buntine

Graph embedding methods transform high-dimensional and complex graph contents into low-dimensional representations. They are useful for a wide range of graph analysis tasks including link prediction, node classification,…

Graph EmbeddingLink PredictionNode Classification

Uncertainty Modeling in Graph Neural Networks via Stochastic Differential Equations

2024-08-28 · Richard Bergna, Sergio Calvo-Ordoñez, Felix L. Opolka, Pietro Liò 외

We address the problem of learning uncertainty-aware representations for graph-structured data. While Graph Neural Ordinary Differential Equations (GNODE) are effective in learning node representations, they fail to quan…

Uncertainty Quantification

Uncertainty Estimation for Heterophilic Graphs Through the Lens of Information Theory

2025-05-28 · Dominik Fuchsgruber, Tom Wollschläger, Johannes Bordne, Stephan Günnemann

While uncertainty estimation for graphs recently gained traction, most methods rely on homophily and deteriorate in heterophilic settings. We address this by analyzing message passing neural networks from an information-…