Graph Structure Learning with Interpretable Bayesian Neural Networks
- URL: http://arxiv.org/abs/2406.14786v1
- Date: Thu, 20 Jun 2024 23:27:41 GMT
- Title: Graph Structure Learning with Interpretable Bayesian Neural Networks
- Authors: Max Wasserman, Gonzalo Mateos,
- Abstract summary: We introduce novel iterations with independently interpretable parameters.
These parameters influence characteristics of the estimated graph, such as edge sparsity.
After unrolling these iterations, prior knowledge over such graph characteristics shape prior distributions.
Fast execution and parameter efficiency allow for high-fidelity posterior approximation.
- Score: 10.957528713294874
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Graphs serve as generic tools to encode the underlying relational structure of data. Often this graph is not given, and so the task of inferring it from nodal observations becomes important. Traditional approaches formulate a convex inverse problem with a smoothness promoting objective and rely on iterative methods to obtain a solution. In supervised settings where graph labels are available, one can unroll and truncate these iterations into a deep network that is trained end-to-end. Such a network is parameter efficient and inherits inductive bias from the optimization formulation, an appealing aspect for data constrained settings in, e.g., medicine, finance, and the natural sciences. But typically such settings care equally about uncertainty over edge predictions, not just point estimates. Here we introduce novel iterations with independently interpretable parameters, i.e., parameters whose values - independent of other parameters' settings - proportionally influence characteristics of the estimated graph, such as edge sparsity. After unrolling these iterations, prior knowledge over such graph characteristics shape prior distributions over these independently interpretable network parameters to yield a Bayesian neural network (BNN) capable of graph structure learning (GSL) from smooth signal observations. Fast execution and parameter efficiency allow for high-fidelity posterior approximation via Markov Chain Monte Carlo (MCMC) and thus uncertainty quantification on edge predictions. Synthetic and real data experiments corroborate this model's ability to provide well-calibrated estimates of uncertainty, in test cases that include unveiling economic sector modular structure from S$\&$P$500$ data and recovering pairwise digit similarities from MNIST images. Overall, this framework enables GSL in modest-scale applications where uncertainty on the data structure is paramount.
Related papers
- The Effectiveness of Curvature-Based Rewiring and the Role of Hyperparameters in GNNs Revisited [0.7373617024876725]
Message passing is the dominant paradigm in Graph Neural Networks (GNNs)
Recent efforts have focused on graph rewiring techniques, which disconnect the input graph originating from the data and the computational graph, on which message passing is performed.
While oversquashing has been demonstrated in synthetic datasets, in this work we reevaluate the performance gains that curvature-based rewiring brings to real-world datasets.
arXiv Detail & Related papers (2024-07-12T16:03:58Z) - Chasing Fairness in Graphs: A GNN Architecture Perspective [73.43111851492593]
We propose textsfFair textsfMessage textsfPassing (FMP) designed within a unified optimization framework for graph neural networks (GNNs)
In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together.
Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets.
arXiv Detail & Related papers (2023-12-19T18:00:15Z) - Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks [32.345435955298825]
Graph Neural Networks (GNNs) are neural models that leverage the dependency structure in graphical data via message passing among the graph nodes.
A main challenge in studying GNN explainability is to provide fidelity measures that evaluate the performance of these explanation functions.
This paper studies this foundational challenge, spotlighting the inherent limitations of prevailing fidelity metrics.
arXiv Detail & Related papers (2023-10-03T06:25:14Z) - Graph Neural Processes for Spatio-Temporal Extrapolation [36.01312116818714]
We study the task of extrapolation-temporal processes that generates data at target locations from surrounding contexts in a graph.
Existing methods either use learning-grained models like Neural Networks or statistical approaches like Gaussian for this task.
We propose Spatio Graph Neural Processes (STGNP), a neural latent variable model which commands these capabilities simultaneously.
arXiv Detail & Related papers (2023-05-30T03:55:37Z) - Uncertainty Quantification over Graph with Conformalized Graph Neural
Networks [52.20904874696597]
Graph Neural Networks (GNNs) are powerful machine learning prediction models on graph-structured data.
GNNs lack rigorous uncertainty estimates, limiting their reliable deployment in settings where the cost of errors is significant.
We propose conformalized GNN (CF-GNN), extending conformal prediction (CP) to graph-based models for guaranteed uncertainty estimates.
arXiv Detail & Related papers (2023-05-23T21:38:23Z) - Accurate Node Feature Estimation with Structured Variational Graph
Autoencoder [21.436706159840014]
Given a graph with partial observations of node features, how can we estimate the missing features accurately?
We propose SVGA (Structured Variational Graph Autoencoder), an accurate method for feature estimation.
As a result, SVGA combines the advantages of probabilistic inference and graph neural networks, achieving state-of-the-art performance in real datasets.
arXiv Detail & Related papers (2022-06-09T14:07:45Z) - 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) - Interpreting Graph Neural Networks for NLP With Differentiable Edge
Masking [63.49779304362376]
Graph neural networks (GNNs) have become a popular approach to integrating structural inductive biases into NLP models.
We introduce a post-hoc method for interpreting the predictions of GNNs which identifies unnecessary edges.
We show that we can drop a large proportion of edges without deteriorating the performance of the model.
arXiv Detail & Related papers (2020-10-01T17:51:19Z) - Unlabelled Data Improves Bayesian Uncertainty Calibration under
Covariate Shift [100.52588638477862]
We develop an approximate Bayesian inference scheme based on posterior regularisation.
We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
arXiv Detail & Related papers (2020-06-26T13:50:19Z) - Residual Correlation in Graph Neural Network Regression [39.54530450932135]
We show that conditional independence assumption severely limits predictive power.
We address this problem with an interpretable and efficient framework.
Our framework achieves substantially higher accuracy than competing baselines.
arXiv Detail & Related papers (2020-02-19T16:32:54Z) - Block-Approximated Exponential Random Graphs [77.4792558024487]
An important challenge in the field of exponential random graphs (ERGs) is the fitting of non-trivial ERGs on large graphs.
We propose an approximative framework to such non-trivial ERGs that result in dyadic independence (i.e., edge independent) distributions.
Our methods are scalable to sparse graphs consisting of millions of nodes.
arXiv Detail & Related papers (2020-02-14T11:42:16Z)
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.