Size-Invariant Graph Representations for Graph Classification
Extrapolations
- URL: http://arxiv.org/abs/2103.05045v1
- Date: Mon, 8 Mar 2021 20:01:59 GMT
- Title: Size-Invariant Graph Representations for Graph Classification
Extrapolations
- Authors: Beatrice Bevilacqua, Yangze Zhou, Bruno Ribeiro
- Abstract summary: In general, graph representation learning methods assume that the test and train data come from the same distribution.
Our work shows it is possible to use a causal model to learn approximately invariant representations that better extrapolate between train and test data.
- Score: 6.143735952091508
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In general, graph representation learning methods assume that the test and
train data come from the same distribution. In this work we consider an
underexplored area of an otherwise rapidly developing field of graph
representation learning: The task of out-of-distribution (OOD) graph
classification, where train and test data have different distributions, with
test data unavailable during training. Our work shows it is possible to use a
causal model to learn approximately invariant representations that better
extrapolate between train and test data. Finally, we conclude with synthetic
and real-world dataset experiments showcasing the benefits of representations
that are invariant to train/test distribution shifts.
Related papers
- PAC Learnability under Explanation-Preserving Graph Perturbations [15.83659369727204]
Graph neural networks (GNNs) operate over graphs, enabling the model to leverage the complex relationships and dependencies in graph-structured data.
A graph explanation is a subgraph which is an almost sufficient' statistic of the input graph with respect to its classification label.
This work considers two methods for leveraging such perturbation invariances in the design and training of GNNs.
arXiv Detail & Related papers (2024-02-07T17:23:15Z) - Graph Fairness Learning under Distribution Shifts [33.9878682279549]
Graph neural networks (GNNs) have achieved remarkable performance on graph-structured data.
GNNs may inherit prejudice from the training data and make discriminatory predictions based on sensitive attributes, such as gender and race.
We propose a graph generator to produce numerous graphs with significant bias and under different distances.
arXiv Detail & Related papers (2024-01-30T06:51:24Z) - GOODAT: Towards Test-time Graph Out-of-Distribution Detection [103.40396427724667]
Graph neural networks (GNNs) have found widespread application in modeling graph data across diverse domains.
Recent studies have explored graph OOD detection, often focusing on training a specific model or modifying the data on top of a well-trained GNN.
This paper introduces a data-centric, unsupervised, and plug-and-play solution that operates independently of training data and modifications of GNN architecture.
arXiv Detail & Related papers (2024-01-10T08:37:39Z) - Graph Out-of-Distribution Generalization with Controllable Data
Augmentation [51.17476258673232]
Graph Neural Network (GNN) has demonstrated extraordinary performance in classifying graph properties.
Due to the selection bias of training and testing data, distribution deviation is widespread.
We propose OOD calibration to measure the distribution deviation of virtual samples.
arXiv Detail & Related papers (2023-08-16T13:10:27Z) - Metric Distribution to Vector: Constructing Data Representation via
Broad-Scale Discrepancies [15.40538348604094]
We present a novel embedding strategy named $mathbfMetricDistribution2vec$ to extract distribution characteristics into the vectorial representation for each data.
We demonstrate the application and effectiveness of our representation method in the supervised prediction tasks on extensive real-world structural graph datasets.
arXiv Detail & Related papers (2022-10-02T03:18:30Z) - Similarity-aware Positive Instance Sampling for Graph Contrastive
Pre-training [82.68805025636165]
We propose to select positive graph instances directly from existing graphs in the training set.
Our selection is based on certain domain-specific pair-wise similarity measurements.
Besides, we develop an adaptive node-level pre-training method to dynamically mask nodes to distribute them evenly in the graph.
arXiv Detail & Related papers (2022-06-23T20:12:51Z) - Discovering Invariant Rationales for Graph Neural Networks [104.61908788639052]
Intrinsic interpretability of graph neural networks (GNNs) is to find a small subset of the input graph's features.
We propose a new strategy of discovering invariant rationale (DIR) to construct intrinsically interpretable GNNs.
arXiv Detail & Related papers (2022-01-30T16:43:40Z) - OOD-GNN: Out-of-Distribution Generalized Graph Neural Network [73.67049248445277]
Graph neural networks (GNNs) have achieved impressive performance when testing and training graph data come from identical distribution.
Existing GNNs lack out-of-distribution generalization abilities so that their performance substantially degrades when there exist distribution shifts between testing and training graph data.
We propose an out-of-distribution generalized graph neural network (OOD-GNN) for achieving satisfactory performance on unseen testing graphs that have different distributions with training graphs.
arXiv Detail & Related papers (2021-12-07T16:29:10Z) - Stable Prediction on Graphs with Agnostic Distribution Shift [105.12836224149633]
Graph neural networks (GNNs) have been shown to be effective on various graph tasks with randomly separated training and testing data.
In real applications, however, the distribution of training graph might be different from that of the test one.
We propose a novel stable prediction framework for GNNs, which permits both locally and globally stable learning and prediction on graphs.
arXiv Detail & Related papers (2021-10-08T02:45:47Z)
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.