A Sparse Tensor Generator with Efficient Feature Extraction

TL;DR

This paper introduces a smart generator for large-scale sparse tensors and efficient methods for feature extraction, facilitating research and analysis in applications like deep learning and social network analysis.

Contribution

The authors present a novel sparse tensor generator that mimics real data and propose optimized feature extraction techniques, addressing dataset scarcity and computational challenges.

Findings

Generated tensors accurately reflect real-world characteristics

Feature extraction methods are computationally efficient

Decomposition performance validates generator quality

Abstract

Sparse tensor operations are increasingly important in diverse applications such as social networks, deep learning, diagnosis, crime, and review analysis. However, a major obstacle in sparse tensor research is the lack of large-scale sparse tensor datasets. Another challenge lies in analyzing sparse tensor features, which are essential not only for understanding the nonzero pattern but also for selecting the most suitable storage format, decomposition algorithm, and reordering methods. However, due to the large size of real-world tensors, even extracting these features can be computationally expensive without careful optimization. To address these limitations, we have developed a smart sparse tensor generator that replicates key characteristics of real sparse tensors. Additionally, we propose efficient methods for extracting a comprehensive set of sparse tensor features. The effectiveness of our generator is validated through the quality of extracted features and the performance of decomposition on the generated tensors. Both the sparse tensor feature extractor and the tensor generator are open source with all the artifacts available at https://github.com/sparcityeu/FeaTensor and https://github.com/sparcityeu/GenTensor, respectively.