Related papers: Learning Latent Graph Structures and their Uncertainty

Learning Latent Graph Structures and their Uncertainty

URL: http://arxiv.org/abs/2405.19933v1
Date: Thu, 30 May 2024 10:49:22 GMT
Title: Learning Latent Graph Structures and their Uncertainty
Authors: Alessandro Manenti, Daniele Zambon, Cesare Alippi,
Abstract summary: Graph Neural Networks (GNNs) use relational information as an inductive bias to enhance the model's accuracy. As task-relevant relations might be unknown, graph structure learning approaches have been proposed to learn them while solving the downstream prediction task.
Score: 63.95971478893842
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Within a prediction task, Graph Neural Networks (GNNs) use relational information as an inductive bias to enhance the model's accuracy. As task-relevant relations might be unknown, graph structure learning approaches have been proposed to learn them while solving the downstream prediction task. In this paper, we demonstrate that minimization of a point-prediction loss function, e.g., the mean absolute error, does not guarantee proper learning of the latent relational information and its associated uncertainty. Conversely, we prove that a suitable loss function on the stochastic model outputs simultaneously grants (i) the unknown adjacency matrix latent distribution and (ii) optimal performance on the prediction task. Finally, we propose a sampling-based method that solves this joint learning task. Empirical results validate our theoretical claims and demonstrate the effectiveness of the proposed approach.

Related papers

Uncertainty for Active Learning on Graphs [70.44714133412592]
Uncertainty Sampling is an Active Learning strategy that aims to improve the data efficiency of machine learning models. We benchmark Uncertainty Sampling beyond predictive uncertainty and highlight a significant performance gap to other Active Learning strategies. We develop ground-truth Bayesian uncertainty estimates in terms of the data generating process and prove their effectiveness in guiding Uncertainty Sampling toward optimal queries.
arXiv Detail & Related papers (2024-05-02T16:50:47Z)
Uncertainty in Graph Neural Networks: A Survey [50.63474656037679]
Graph Neural Networks (GNNs) have been extensively used in various real-world applications. However, the predictive uncertainty of GNNs stemming from diverse sources can lead to unstable and erroneous predictions. This survey aims to provide a comprehensive overview of the GNNs from the perspective of uncertainty.
arXiv Detail & Related papers (2024-03-11T21:54:52Z)
Less is More: Rethinking Few-Shot Learning and Recurrent Neural Nets [2.824895388993495]
We provide theoretical guarantees for reliable learning under the information-theoretic AEP. We then focus on a highly efficient recurrent neural net (RNN) framework and propose a reduced-entropy algorithm for few-shot learning. Our experimental results demonstrate significant potential for improving learning models' sample efficiency, generalization, and time complexity.
arXiv Detail & Related papers (2022-09-28T17:33:11Z)
Robust Causal Graph Representation Learning against Confounding Effects [21.380907101361643]
We propose Robust Causal Graph Representation Learning (RCGRL) to learn robust graph representations against confounding effects. RCGRL introduces an active approach to generate instrumental variables under unconditional moment restrictions, which empowers the graph representation learning model to eliminate confounders.
arXiv Detail & Related papers (2022-08-18T01:31:25Z)
Sparse Graph Learning from Spatiotemporal Time Series [16.427698929775023]
We propose a graph learning framework that learns the relational dependencies as distributions over graphs. We show that the proposed solution can be used as a stand-alone graph identification procedure as well as a graph learning component of an end-to-end forecasting architecture.
arXiv Detail & Related papers (2022-05-26T17:02:43Z)
Bayesian Graph Contrastive Learning [55.36652660268726]
We propose a novel perspective of graph contrastive learning methods showing random augmentations leads to encoders. Our proposed method represents each node by a distribution in the latent space in contrast to existing techniques which embed each node to a deterministic vector. We show a considerable improvement in performance compared to existing state-of-the-art methods on several benchmark datasets.
arXiv Detail & Related papers (2021-12-15T01:45:32Z)
Distributionally Robust Semi-Supervised Learning Over Graphs [68.29280230284712]
Semi-supervised learning (SSL) over graph-structured data emerges in many network science applications. To efficiently manage learning over graphs, variants of graph neural networks (GNNs) have been developed recently. Despite their success in practice, most of existing methods are unable to handle graphs with uncertain nodal attributes. Challenges also arise due to distributional uncertainties associated with data acquired by noisy measurements. A distributionally robust learning framework is developed, where the objective is to train models that exhibit quantifiable robustness against perturbations.
arXiv Detail & Related papers (2021-10-20T14:23:54Z)
Learning Graphs from Smooth Signals under Moment Uncertainty [23.868075779606425]
We consider the problem of inferring the graph structure from a given set of graph signals. Traditional graph learning models do not take this distributional uncertainty into account.
arXiv Detail & Related papers (2021-05-12T06:47:34Z)
Graph Embedding with Data Uncertainty [113.39838145450007]
spectral-based subspace learning is a common data preprocessing step in many machine learning pipelines. Most subspace learning methods do not take into consideration possible measurement inaccuracies or artifacts that can lead to data with high uncertainty.
arXiv Detail & Related papers (2020-09-01T15:08:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.