skip to main content

Title: Improved Dynamic Graph Learning through Fault-Tolerant Sparsification
Graph sparsification has been used to improve the computational cost of learning over graphs, e.g., Laplacian-regularized estimation and graph semi-supervised learning (SSL). However, when graphs vary over time, repeated sparsification requires polynomial order computational cost per update. We propose a new type of graph sparsification namely fault-tolerant (FT) sparsification to significantly reduce the cost to only a constant. Then the computational cost of subsequent graph learning tasks can be significantly improved with limited loss in their accuracy. In particular, we give theoretical analyze to upper bound the loss in the accuracy of the subsequent Laplacian-regularized estimation and graph SSL, due to the FT sparsification. In addition, FT spectral sparsification can be generalized to FT cut sparsification, for cut-based graph learning. Extensive experiments have confirmed the computational efficiencies and accuracies of the proposed methods for learning on dynamic graphs.
; ; ; ;
Award ID(s):
Publication Date:
Journal Name:
Proceedings of the 36th International Conference on Machine Learning
Page Range or eLocation-ID:
Sponsoring Org:
National Science Foundation
More Like this
  1. Recent spectral graph sparsification techniques have shown promising performance in accelerating many numerical and graph algorithms, such as iterative methods for solving large sparse matrices, spectral partitioning of undirected graphs, vectorless verification of power/thermal grids, representation learning of large graphs, etc. However, prior spectral graph sparsification methods rely on fast Laplacian matrix solvers that are usually challenging to implement in practice. This work, for the first time, introduces a solver-free approach (SF-GRASS) for spectral graph sparsification by leveraging emerging spectral graph coarsening and graph signal processing (GSP) techniques. We introduce a local spectral embedding scheme for efficiently identifying spectrally-critical edgesmore »that are key to preserving graph spectral properties, such as the first few Laplacian eigenvalues and eigenvectors. Since the key kernel functions in SF-GRASS can be efficiently implemented using sparse-matrix-vector-multiplications (SpMVs), the proposed spectral approach is simple to implement and inherently parallel friendly. Our extensive experimental results show that the proposed method can produce a hierarchy of high-quality spectral sparsifiers in nearly-linear time for a variety of real-world, large-scale graphs and circuit networks when compared with prior state-of-the-art spectral methods.« less
  2. Computing similarity between graphs is a fundamental and critical problem in graph-based applications, and one of the most commonly used graph similarity measures is graph edit distance (GED), defined as the minimum number of graph edit operations that transform one graph to another. Existing GED solutions suffer from severe performance issues due in particular to the NP-hardness of exact GED computation. Recently, deep learning has shown early promise for GED approximation with high accuracy and low computational cost. However, existing methods treat GED as a global, coarse-grained graph similarity value, while neglecting the type-specific transformative impacts incurred by different typesmore »of graph edit operations, including node insertion/deletion, node relabeling, edge insertion/deletion, and edge relabeling. In this paper, we propose a type-aware graph similarity learning and computation framework, TaGSim (T ype -a ware G raph Sim ilarity), that estimates GED in a fine-grained approach w.r.t. different graph edit types. Specifically, for each type of graph edit operations, TaGSim models its unique transformative impacts upon graphs, and encodes them into high-quality, type-aware graph embeddings, which are further fed into type-aware neural networks for accurate GED estimation. Extensive experiments on five real-world datasets demonstrate the effectiveness and efficiency of TaGSim, which significantly outperforms state-of-the-art GED solutions.« less
  3. Recently there has been significant interest in using machine learning to improve the accuracy of cardinality estimation. This work has focused on improving average estimation error, but not all estimates matter equally for downstream tasks like query optimization. Since learned models inevitably make mistakes, the goal should be to improve the estimates that make the biggest difference to an optimizer. We introduce a new loss function, Flow-Loss, for learning cardinality estimation models. Flow-Loss approximates the optimizer's cost model and search algorithm with analytical functions, which it uses to optimize explicitly for better query plans. At the heart of Flow-Loss ismore »a reduction of query optimization to a flow routing problem on a certain "plan graph", in which different paths correspond to different query plans. To evaluate our approach, we introduce the Cardinality Estimation Benchmark (CEB) which contains the ground truth cardinalities for sub-plans of over 16 K queries from 21 templates with up to 15 joins. We show that across different architectures and databases, a model trained with Flow-Loss improves the plan costs and query runtimes despite having worse estimation accuracy than a model trained with Q-Error. When the test set queries closely match the training queries, models trained with both loss functions perform well. However, the Q-Error-trained model degrades significantly when evaluated on slightly different queries (e.g., similar but unseen query templates), while the Flow-Loss-trained model generalizes better to such situations, achieving 4 -- 8× better 99th percentile runtimes on unseen templates with the same model architecture and training data.« less
  4. Graph compression or sparsification is a basic information-theoretic and computational question. A major open problem in this research area is whether $(1+\epsilon)$-approximate cut-preserving vertex sparsifiers with size close to the number of terminals exist. As a step towards this goal, we initiate the study of a thresholded version of the problem: for a given parameter $c$, find a smaller graph, which we call \emph{connectivity-$c$ mimicking network}, which preserves connectivity among $k$ terminals exactly up to the value of $c$. We show that connectivity-$c$ mimicking networks of size $O(kc^4)$ exist and can be found in time $m(c\log n)^{O(c)}$. We also givemore »a separate algorithm that constructs such graphs of size $k \cdot O(c)^{2c}$ in time $mc^{O(c)}\log^{O(1)}n$. These results lead to the first offline data structures for answering fully dynamic $c$-edge-connectivity queries for $c \ge 4$ in polylogarithmic time per query as well as more efficient algorithms for survivable network design on bounded treewidth graphs.« less
  5. The application of graph Laplacian eigenvectors has been quite popular in the graph signal processing field: one can use them as ingredients to design smooth multiscale basis. Our long-term goal is to study and understand the dual geometry of graph Laplacian eigenvectors. In order to do that, it is necessary to define a certain metric to measure the behavioral differences between each pair of the eigenvectors. Saito (2018) considered the ramified optimal transportation (ROT) cost between the square of the eigenvectors as such a metric. Clonginger and Steinerberger (2018) proposed a way to measure the affinity (or `similarity') between themore »eigenvectors based on their Hadamard (HAD) product. In this article, we propose a simplified ROT metric that is more computational efficient and introduce two more ways to define the distance between the eigenvectors, i.e., the time-stepping diffusion (TSD) metric and the difference of absolute gradient (DAG) pseudometric. The TSD metric measures the cost of "flattening" the initial graph signal via diffusion process up to certain time, hence it can be viewed as a time-dependent version of the ROT metric. The DAG pseudometric is the l2-distance between the feature vectors derived from the eigenvectors, in particular, the absolute gradients of the eigenvectors. We then compare the performance of ROT, HAD and the two new "metrics: on different kinds of graphs. Finally, we investigate their relationship as well as their pros and cons. Keywords: Graph Laplacian eigenvectors, metrics between orthonormal vectors, dual geometry of graph Laplacian eigenvectors, multiscale basis dictionaries on graphs, heat diffusion on graphs, Wasserstein distance, optimal transport« less