Benchmarking Graph Neural Networks

Dwivedi, Vijay Prakash; Joshi, Chaitanya K.; Luu, Anh Tuan; Thomas, L.; Bengio, Yoshua; Bresson, Xavier

doi:10.48550/arxiv.2003.00982

Cited by 119 publications

(232 citation statements)

References 0 publications

Supporting

Mentioning

230

Contrasting

Order By: Relevance

“…Assuming the CNN predictions are mostly accurate (results in Table II), the correctly-predicted branches can be used to provide canonical positional encodings because their locations are consistently defined (up, down, left, and right) according to the airway tree anatomy. Many existing positional encoding methods, i.e., Laplacian eigenvectors [29], randomwalks encodings [30], and encodings using random anchors [16] provide non-canonical positional encodings because these methods operate on arbitrary graphs. By adding leaf branches, the anchors distribute evenly in terms of the depth of the tree, preventing selecting anchors from only upper side of the tree.…”

Section: A Airway Labeling Frameworkmentioning

confidence: 99%

Structure and position-aware graph neural network for airway labeling

Xie¹,

Jacobs²,

Charbonnier³

et al. 2022

Preprint

View full text Add to dashboard Cite

We present a novel graph-based approach for labeling the anatomical branches of a given airway tree segmentation. The proposed method formulates airway labeling as a branch classification problem in the airway tree graph, where branch features are extracted using convolutional neural networks (CNN) and enriched using graph neural networks. Our graph neural network is structure-aware by having each node aggregate information from its local neighbors and position-aware by encoding node positions in the graph.We evaluated the proposed method on 220 airway trees from subjects with various severity stages of Chronic Obstructive Pulmonary Disease (COPD). The results demonstrate that our approach is computationally efficient and significantly improves branch classification performance than the baseline method.The overall average accuracy of our method reaches 91.18% for labeling all 18 segmental airway branches, compared to 83.83% obtained by the standard CNN method. We published our source code at https://github.com/DIAGNijmegen/spgnn. The proposed algorithm is also publicly available at https://grandchallenge.org/algorithms/airway-anatomical-labeling/.

show abstract

Section: A Airway Labeling Frameworkmentioning

confidence: 99%

Structure and position-aware graph neural network for airway labeling

Xie¹,

Jacobs²,

Charbonnier³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…GPUs consume a lot of energy and time. To explore the energy-saving potential on GPUs, we run five applications in AIBench [13] and benchmarking-gnns [16] on all combinations of SM and memory clock frequencies and select the best configurations for minimal energy consumption within the slowdown constraint of 5%. Figure 1 shows the oracle results of energy saving, slowdown, and ED2P (Energy × Dealy 2 ) saving.…”

Section: Energy Optimization Potentialmentioning

confidence: 99%

“…The more similar the curves are, the closer the candidate period is to the actual period. So we evaluate the similarity of each pair of adjacent sub-curves (line [5][6][7][8][9][10][11][12][13][14][15][16][17][18].…”

Section: Feature Sequence Similarity: Find Accurate Periodsmentioning

confidence: 99%

“…Later, we calculate the symmetric mean absolute percentage error (SMAPE) of the current group pair (line 14). Finally, we calculate the weighted average of all SMAPEs as similarity error (line [16][17]. The weights are the numbers of sampling points in groups.…”

Section: Feature Sequence Similarity: Find Accurate Periodsmentioning

confidence: 99%

“…If the difference of these periods is less than the threshold, set SmpDur next = −1 to indicate stop sampling. Otherwise, calculate SmpDur next (line [16][17][18][19][20][21]. The best period, namely T iter , is the period with the minimal error (line 15).…”

mentioning

confidence: 99%

See 2 more Smart Citations

Dynamic GPU Energy Optimization for Machine Learning Training Workloads

Wang,

Zhang,

Lai

et al. 2022

Preprint

View full text Add to dashboard Cite

GPUs are widely used to accelerate the training of machine learning workloads. As modern machine learning models become increasingly larger, they require a longer time to train, leading to higher GPU energy consumption. This paper presents GPOEO, an online GPU energy optimization framework for machine learning training workloads. GPOEO dynamically determines the optimal energy configuration by employing novel techniques for online measurement, multi-objective prediction modeling, and search optimization. To characterize the target workload behavior, GPOEO utilizes GPU performance counters. To reduce the performance counter profiling overhead, it uses an analytical model to detect the training iteration change and only collects performance counter data when an iteration shift is detected. GPOEO employs multi-objective models based on gradient boosting and a local search algorithm to find a trade-off between execution time and energy consumption. We evaluate the GPOEO by applying it to 71 machine learning workloads from two AI benchmark suites running on an NVIDIA RTX3080Ti GPU. Compared with the NVIDIA default scheduling strategy, GPOEO delivers a mean energy saving of 16.2% with a modest average execution time increase of 5.1%.

show abstract

Parallel Clique-Like Subgraph Counting and Listing

Yang

Yan

Zhou

et al. 2019

Conceptual Modeling

View full text Add to dashboard Cite

Using graph neural networks (GNNs) to approximate specific functions such as counting graph substructures is a recent trend in graph learning. Among these works, a popular way is to use subgraph GNNs, which decompose the input graph into a collection of subgraphs and enhance the representation of the graph by applying GNN to individual subgraphs. Although subgraph GNNs are able to count complicated substructures, they suffer from high computational and memory costs. In this paper, we address a non-trivial question: can we count substructures efficiently with GNNs? To answer the question, we first theoretically show that the distance to the rooted nodes within subgraphs is key to boosting the counting power of subgraph GNNs. We then encode such information into structural embeddings, and precompute the embeddings to avoid extracting information over all subgraphs via GNNs repeatedly. Experiments on various benchmarks show that the proposed model can preserve the counting power of subgraph GNNs while running orders of magnitude faster.

show abstract

Benchmarking Graph Neural Networks

Cited by 119 publications

References 0 publications

Structure and position-aware graph neural network for airway labeling

Structure and position-aware graph neural network for airway labeling

Dynamic GPU Energy Optimization for Machine Learning Training Workloads

Parallel Clique-Like Subgraph Counting and Listing

Contact Info

Product

Resources

About