Estimating Aggregate Properties In Relational Networks With Unobserved
Data
- URL: http://arxiv.org/abs/2001.05617v2
- Date: Mon, 27 Jan 2020 00:50:57 GMT
- Title: Estimating Aggregate Properties In Relational Networks With Unobserved
Data
- Authors: Varun Embar, Sriram Srinivasan, Lise Getoor
- Abstract summary: We study the effectiveness of machine learning approaches in estimating aggregate properties on networks with missing attributes.
We show that SRL-based approaches tend to outperform GNN-based approaches both in computing aggregate properties and predictive accuracy.
- Score: 18.753170947851256
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Aggregate network properties such as cluster cohesion and the number of
bridge nodes can be used to glean insights about a network's community
structure, spread of influence and the resilience of the network to faults.
Efficiently computing network properties when the network is fully observed has
received significant attention (Wasserman and Faust 1994; Cook and Holder
2006), however the problem of computing aggregate network properties when there
is missing data attributes has received little attention. Computing these
properties for networks with missing attributes involves performing inference
over the network. Statistical relational learning (SRL) and graph neural
networks (GNNs) are two classes of machine learning approaches well suited for
inferring missing attributes in a graph. In this paper, we study the
effectiveness of these approaches in estimating aggregate properties on
networks with missing attributes. We compare two SRL approaches and three GNNs.
For these approaches we estimate these properties using point estimates such as
MAP and mean. For SRL-based approaches that can infer a joint distribution over
the missing attributes, we also estimate these properties as an expectation
over the distribution. To compute the expectation tractably for probabilistic
soft logic, one of the SRL approaches that we study, we introduce a novel
sampling framework. In the experimental evaluation, using three benchmark
datasets, we show that SRL-based approaches tend to outperform GNN-based
approaches both in computing aggregate properties and predictive accuracy.
Specifically, we show that estimating the aggregate properties as an
expectation over the joint distribution outperforms point estimates.
Related papers
- Initial Investigation of Kolmogorov-Arnold Networks (KANs) as Feature Extractors for IMU Based Human Activity Recognition [5.067238125081022]
We implement KAN as the feature extraction architecture for IMU-based human activity recognition tasks.
We present an initial performance investigation of the KAN-based feature extractor on four public HAR datasets.
arXiv Detail & Related papers (2024-06-16T19:56:03Z) - Exact Recovery and Bregman Hard Clustering of Node-Attributed Stochastic
Block Model [0.16385815610837165]
This paper presents an information-theoretic criterion for the exact recovery of community labels.
It shows how network and attribute information can be exchanged in order to have exact recovery.
It also presents an iterative clustering algorithm that maximizes the joint likelihood.
arXiv Detail & Related papers (2023-10-30T16:46:05Z) - Distributed Learning over Networks with Graph-Attention-Based
Personalization [49.90052709285814]
We propose a graph-based personalized algorithm (GATTA) for distributed deep learning.
In particular, the personalized model in each agent is composed of a global part and a node-specific part.
By treating each agent as one node in a graph the node-specific parameters as its features, the benefits of the graph attention mechanism can be inherited.
arXiv Detail & Related papers (2023-05-22T13:48:30Z) - Batch-Ensemble Stochastic Neural Networks for Out-of-Distribution
Detection [55.028065567756066]
Out-of-distribution (OOD) detection has recently received much attention from the machine learning community due to its importance in deploying machine learning models in real-world applications.
In this paper we propose an uncertainty quantification approach by modelling the distribution of features.
We incorporate an efficient ensemble mechanism, namely batch-ensemble, to construct the batch-ensemble neural networks (BE-SNNs) and overcome the feature collapse problem.
We show that BE-SNNs yield superior performance on several OOD benchmarks, such as the Two-Moons dataset, the FashionMNIST vs MNIST dataset, FashionM
arXiv Detail & Related papers (2022-06-26T16:00:22Z) - Understanding the Distributions of Aggregation Layers in Deep Neural
Networks [8.784438985280092]
aggregation functions as an important mechanism for consolidating deep features into a more compact representation.
In particular, the proximity of global aggregation layers to the output layers of DNNs mean that aggregated features have a direct influence on the performance of a deep net.
We propose a novel mathematical formulation for analytically modelling the probability distributions of output values of layers involved with deep feature aggregation.
arXiv Detail & Related papers (2021-07-09T14:23:57Z) - Deep Attributed Network Representation Learning via Attribute Enhanced
Neighborhood [10.954489956418191]
Attributed network representation learning aims at learning node embeddings by integrating network structure and attribute information.
It is a challenge to fully capture the microscopic structure and the attribute semantics simultaneously.
We propose a deep attributed network representation learning via attribute enhanced neighborhood (DANRL-ANE) model to improve the robustness and effectiveness of node representations.
arXiv Detail & Related papers (2021-04-12T07:03:16Z) - Anomaly Detection on Attributed Networks via Contrastive Self-Supervised
Learning [50.24174211654775]
We present a novel contrastive self-supervised learning framework for anomaly detection on attributed networks.
Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair.
A graph neural network-based contrastive learning model is proposed to learn informative embedding from high-dimensional attributes and local structure.
arXiv Detail & Related papers (2021-02-27T03:17:20Z) - Self-Challenging Improves Cross-Domain Generalization [81.99554996975372]
Convolutional Neural Networks (CNN) conduct image classification by activating dominant features that correlated with labels.
We introduce a simple training, Self-Challenging Representation (RSC), that significantly improves the generalization of CNN to the out-of-domain data.
RSC iteratively challenges the dominant features activated on the training data, and forces the network to activate remaining features that correlates with labels.
arXiv Detail & Related papers (2020-07-05T21:42:26Z) - ReActNet: Towards Precise Binary Neural Network with Generalized
Activation Functions [76.05981545084738]
We propose several ideas for enhancing a binary network to close its accuracy gap from real-valued networks without incurring any additional computational cost.
We first construct a baseline network by modifying and binarizing a compact real-valued network with parameter-free shortcuts.
We show that the proposed ReActNet outperforms all the state-of-the-arts by a large margin.
arXiv Detail & Related papers (2020-03-07T02:12:02Z) - Distribution Approximation and Statistical Estimation Guarantees of
Generative Adversarial Networks [82.61546580149427]
Generative Adversarial Networks (GANs) have achieved a great success in unsupervised learning.
This paper provides approximation and statistical guarantees of GANs for the estimation of data distributions with densities in a H"older space.
arXiv Detail & Related papers (2020-02-10T16:47:57Z) - Predicting Attributes of Nodes Using Network Structure [0.34998703934432673]
We propose an approach to represent a node by a feature map with respect to an attribute $a_i$ using all attributes of neighbors to predict attributes values for $a_i$.
We perform extensive experimentation on ten real-world datasets and show that the proposed feature map significantly improves the prediction accuracy as compared to baseline approaches on these datasets.
arXiv Detail & Related papers (2019-12-27T17:59:33Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.