Machine learning frameworks such as graph neural networks typically rely on a given, fixed
graph to exploit relational inductive biases and thus effectively learn from network data.
However, when said graphs are (partially) unobserved, noisy, or dynamic, the problem
of inferring graph structure from data becomes relevant. In this paper, we postulate a
graph convolutional relationship between the observed and latent graphs, and formulate
the graph structure learning task as a network inverse (deconvolution) problem. In lieu of
eigendecomposition-based spectral methods or iterative optimization solutions, we unroll and
truncate proximal gradient iterations to arrive at a parameterized neural network architecture
that we call a Graph Deconvolution Network (GDN). GDNs can learn a distribution of graphs
in a supervised fashion, perform link prediction or edge-weight regression tasks by adapting
the loss function, and they are inherently inductive as well as node permutation equivariant.
We corroborate GDN’s superior graph learning performance and its generalization to larger
graphs using synthetic data in supervised settings. Moreover, we demonstrate the robustness and representation power of GDNs on real world neuroimaging and social network datasets.
more »
« less
Graph Regression and Classification using Permutation Invariant Representations
We address the problem of graph regression using graph convolutional
neural networks and permutation invariant representation.
Many graph neural network algorithms can be abstracted
as a series of message passing functions between the
nodes, ultimately producing a set of latent features for each
node. Processing these latent features to produce a single estimate
over the entire graph is dependent on how the nodes are
ordered in the graph’s representation. We propose a permutation
invariant mapping that produces graph representations
that are invariant to any ordering of the nodes. This mapping
can serve as a pivotal piece in leveraging graph convolutional
networks for graph classification and graph regression problems.
We tested out this method and validated our solution on
the QM9 dataset.
more »
« less
- NSF-PAR ID:
- 10392152
- Date Published:
- Journal Name:
- AAAI/Graphs and more Complex structures for Learning and Reasoning Workshop
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Graphs/Networks are common in real-world applications where data have rich content and complex relationships. The increasing popularity also motivates many network learning algorithms, such as community detection, clustering, classification, and embedding learning, etc.. In reality, the large network volumes often hider a direct use of learning algorithms to the graphs. As a result, it is desirable to have the flexibility to condense a network to an arbitrary size, with well-preserved network topology and node content information. In this paper, we propose a graph compression network (GEN) to achieve network compression and embedding at the same time. Our theme is to leverage the network topology to find node mappings, such that densely connected nodes, including their node content, are compressed as a new node, with a latent vector (i.e. embedding) being learned to represent the compressed node. In addition to compression learning, we also develop a novel encoding-decoding framework, using feature diffusion process, to "decompress" the condensed network. Different from traditional graph convolution which uses direct-neighbor message passing, our decompression advocates high-order message passing within compressed nodes to learning feature representation for all nodes in the network. A unique strength of GEN is that it leverages the graph neural network principle to learn mapping automatically, so one can compress a network to an arbitrary size, and also decompress it to the original node space with minimum information loss. Experiments and comparisons confirm that GEN can automatically find clusters and communities, and compress them as new nodes. Results also show that GEN achieves improved performance for numerous tasks, including graph classification and node clustering.more » « less
-
Given earth imagery with spectral features on a terrain surface, this paper studies surface segmentation based on both explanatory features and surface topology. The problem is important in many spatial and spatiotemporal applications such as flood extent mapping in hydrology. The problem is uniquely challenging for several reasons: first, the size of earth imagery on a terrain surface is often much larger than the input of popular deep convolutional neural networks; second, there exists topological structure dependency between pixel classes on the surface, and such dependency can follow an unknown and non-linear distribution; third, there are often limited training labels. Existing methods for earth imagery segmentation often divide the imagery into patches and consider the elevation as an additional feature channel. These methods do not fully incorporate the spatial topological structural constraint within and across surface patches and thus often show poor results, especially when training labels are limited. Existing methods on semi-supervised and unsupervised learning for earth imagery often focus on learning representation without explicitly incorporating surface topology. In contrast, we propose a novel framework that explicitly models the topological skeleton of a terrain surface with a contour tree from computational topology, which is guided by the physical constraint (e.g., water flow direction on terrains). Our framework consists of two neural networks: a convolutional neural network (CNN) to learn spatial contextual features on a 2D image grid, and a graph neural network (GNN) to learn the statistical distribution of physics-guided spatial topological dependency on the contour tree. The two models are co-trained via variational EM. Evaluations on the real-world flood mapping datasets show that the proposed models outperform baseline methods in classification accuracy, especially when training labels are limited.more » « less
-
Unlike images which are represented in regular dense grids, 3D point clouds are irregular and unordered, hence applying convolution on them can be difficult. In this paper, we extend the dynamic filter to a new convolution operation, named PointConv. PointConv can be applied on point clouds to build deep convolutional networks. We treat convolution kernels as nonlinear functions of the local coordinates of 3D points comprised of weight and density functions. With respect to a given point, the weight functions are learned with multi-layer perceptron networks and the density functions through kernel density estimation. A novel reformulation is proposed for efficiently computing the weight functions, which allowed us to dramatically scale up the network and significantly improve its performance. The learned convolution kernel can be used to compute translation-invariant and permutation-invariant convolution on any point set in the 3D space. Besides, PointConv can also be used as deconvolution operators to propagate features from a subsampled point cloud back to its original resolution. Experiments on ModelNet40, ShapeNet, and ScanNet show that deep convolutional neural networks built on PointConv are able to achieve state-of-the-art on challenging semantic segmentation benchmarks on 3D point clouds. Besides, our experiments converting CIFAR-10 into a point cloud showed that networks built on PointConv can match the performance of convolutional networks in 2D images of a similar structure.more » « less
-
more » « less
Abstract Graph representation learning has revolutionized many artificial intelligence and machine learning tasks in recent years, ranging from combinatorial optimization, drug discovery, recommendation systems, image classification, social network analysis to natural language understanding. This paper shows their efficacy in modeling relationships between products and making predictions for unseen product networks. By representing products as nodes and their relationships as edges of a graph, we show how an inductive graph neural network approach, named GraphSAGE, can efficiently learn continuous representations for nodes and edges. These representations also capture product feature information such as price, brand, and engineering attributes. They are combined with a classification model for predicting the existence of a relationship between any two products. Using a case study of the Chinese car market, we find that our method yields double the F-1 score compared to an Exponential Random Graph Model-based method for predicting the co-consideration relationship between cars. While a vanilla Graph-SAGE requires a partial network to make predictions, we augment it with an ‘adjacency prediction model’ to circumvent this limitation. This enables us to predict product relationships when no neighborhood information is known. Finally, we demonstrate how a permutation-based interpretability analysis can provide insights on how design attributes impact the predictions of relationships between products. Overall, this work provides a systematic method to predict the relationships between products in a complex engineering system.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
