Amortized Probabilistic Detection of Communities in Graphs
- URL: http://arxiv.org/abs/2010.15727v3
- Date: Tue, 15 Jun 2021 08:07:29 GMT
- Title: Amortized Probabilistic Detection of Communities in Graphs
- Authors: Yueqi Wang, Yoonho Lee, Pallab Basu, Juho Lee, Yee Whye Teh, Liam
Paninski, Ari Pakman
- Abstract summary: We propose a simple framework for amortized community detection.
We combine the expressive power of GNNs with recent methods for amortized clustering.
We evaluate several models from our framework on synthetic and real datasets.
- Score: 49.46170819501234
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Learning community structures in graphs has broad applications across
scientific domains. While graph neural networks (GNNs) have been successful in
encoding graph structures, existing GNN-based methods for community detection
are limited by requiring knowledge of the number of communities in advance, in
addition to lacking a proper probabilistic formulation to handle uncertainty.
We propose a simple framework for amortized community detection, which
addresses both of these issues by combining the expressive power of GNNs with
recent methods for amortized clustering. Our models consist of a graph
representation backbone that extracts structural information and an amortized
clustering network that naturally handles variable numbers of clusters. Both
components combine into well-defined models of the posterior distribution of
graph communities and are jointly optimized given labeled graphs. At inference
time, the models yield parallel samples from the posterior of community labels,
quantifying uncertainty in a principled way. We evaluate several models from
our framework on synthetic and real datasets and demonstrate superior
performance to previous methods. As a separate contribution, we extend recent
amortized probabilistic clustering architectures by adding attention modules,
which yield further improvements on community detection tasks.
Related papers
- Modularity aided consistent attributed graph clustering via coarsening [6.522020196906943]
Graph clustering is an important unsupervised learning technique for partitioning graphs with attributes and detecting communities.
We propose a loss function incorporating log-determinant, smoothness, and modularity components using a block majorization-minimization technique.
Our algorithm seamlessly integrates graph neural networks (GNNs) and variational graph autoencoders (VGAEs) to learn enhanced node features and deliver exceptional clustering performance.
arXiv Detail & Related papers (2024-07-09T10:42:19Z) - Synergistic Deep Graph Clustering Network [14.569867830074292]
We propose a graph clustering framework named Synergistic Deep Graph Clustering Network (SynC)
In our approach, we design a Transform Input Graph Auto-Encoder (TIGAE) to obtain high-quality embeddings for guiding structure augmentation.
Notably, representation learning and structure augmentation share weights, significantly reducing the number of model parameters.
arXiv Detail & Related papers (2024-06-22T09:40:34Z) - Homophily-enhanced Structure Learning for Graph Clustering [19.586401211161846]
Graph structure learning allows refining the input graph by adding missing links and removing spurious connections.
Previous endeavors in graph structure learning have predominantly centered around supervised settings.
We propose a novel method called textbfhomophily-enhanced structure textbflearning for graph clustering (HoLe)
arXiv Detail & Related papers (2023-08-10T02:53:30Z) - DEGREE: Decomposition Based Explanation For Graph Neural Networks [55.38873296761104]
We propose DEGREE to provide a faithful explanation for GNN predictions.
By decomposing the information generation and aggregation mechanism of GNNs, DEGREE allows tracking the contributions of specific components of the input graph to the final prediction.
We also design a subgraph level interpretation algorithm to reveal complex interactions between graph nodes that are overlooked by previous methods.
arXiv Detail & Related papers (2023-05-22T10:29:52Z) - Interpolation-based Correlation Reduction Network for Semi-Supervised
Graph Learning [49.94816548023729]
We propose a novel graph contrastive learning method, termed Interpolation-based Correlation Reduction Network (ICRN)
In our method, we improve the discriminative capability of the latent feature by enlarging the margin of decision boundaries.
By combining the two settings, we extract rich supervision information from both the abundant unlabeled nodes and the rare yet valuable labeled nodes for discnative representation learning.
arXiv Detail & Related papers (2022-06-06T14:26:34Z) - A Variational Edge Partition Model for Supervised Graph Representation
Learning [51.30365677476971]
This paper introduces a graph generative process to model how the observed edges are generated by aggregating the node interactions over a set of overlapping node communities.
We partition each edge into the summation of multiple community-specific weighted edges and use them to define community-specific GNNs.
A variational inference framework is proposed to jointly learn a GNN based inference network that partitions the edges into different communities, these community-specific GNNs, and a GNN based predictor that combines community-specific GNNs for the end classification task.
arXiv Detail & Related papers (2022-02-07T14:37:50Z) - Crime Prediction with Graph Neural Networks and Multivariate Normal
Distributions [18.640610803366876]
We tackle the sparsity problem in high resolution by leveraging the flexible structure of graph convolutional networks (GCNs)
We build our model with Graph Convolutional Gated Recurrent Units (Graph-ConvGRU) to learn spatial, temporal, and categorical relations.
We show that our model is not only generative but also precise.
arXiv Detail & Related papers (2021-11-29T17:37:01Z) - Graph Neural Networks for Inconsistent Cluster Detection in Incremental
Entity Resolution [3.4806267677524896]
In mature data repositories, the relationships may be mostly correct but require incremental improvements owing to errors in the original data or in the entity resolution system.
This paper proposes a novel method for identifying inconsistent clusters (IC), existing groups of related products that do not belong together.
We demonstrate that existing Message Passing neural networks perform well at this task, exceeding traditional graph processing techniques.
arXiv Detail & Related papers (2021-05-12T20:39:22Z) - Structured Graph Learning for Clustering and Semi-supervised
Classification [74.35376212789132]
We propose a graph learning framework to preserve both the local and global structure of data.
Our method uses the self-expressiveness of samples to capture the global structure and adaptive neighbor approach to respect the local structure.
Our model is equivalent to a combination of kernel k-means and k-means methods under certain condition.
arXiv Detail & Related papers (2020-08-31T08:41:20Z) - Structural Landmarking and Interaction Modelling: on Resolution Dilemmas
in Graph Classification [50.83222170524406]
We study the intrinsic difficulty in graph classification under the unified concept of resolution dilemmas''
We propose SLIM'', an inductive neural network model for Structural Landmarking and Interaction Modelling.
arXiv Detail & Related papers (2020-06-29T01:01:42Z)
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.