Effective and lightweight lossy compression of tensors: techniques and applications

Jihoon Ko, Taehyung Kwon, Jinhong Jung, Kijung Shin

Abstract: Many real-world data from various domains can be represented as tensors, and a significant portion of them is large scale. Thus, tensor compression is crucial for their storage and transmission. Recently, deep learning-based methods have emerged to enhance compression performance. However, they require considerable compression time to fulfill their performance. In this work, to achieve both speed and performance, we develop ELiCiT, an effective and lightweight lossy tensor compression method. When designing ELiCiT, we avoid deep auto-regressive neural networks and index reordering, which incur high computational costs of deep learning-based tensor compression. Specifically, instead of using the orders of indices as parameters, we introduce a feature-based model for indices, which enhances the model’s expressive capacity and simplifies the overall end-to-end training procedure. Moreover, to reduce the size of the parameters and computational cost for inference, we adopt end-to-end clustering-based quantization, as an alternative to deep auto-regressive architecture. As a result, ELiCiT becomes easy to optimize with enhanced expressiveness. We prove that it (partially) generalizes deep learning-based methods and also traditional ones. Using eight real-world tensors, we show that ELiCiT yields compact outputs that fit the input tensor accurately. Compared to the best competitor with similar fitness, it offers 1.51\(-\)5.05\(\times \) smaller outputs. Moreover, compared to deep learning-based compression methods, ELiCiT is 11.8\(-\)96.0\(\times \) faster with 5–48% better fitness for a similarly sized output. We also demonstrate that ELiCiT is extended to matrix completion, neural network compression , and tensor stream summarization, providing the best trade-offs between model size and application performance.

External IDs:dblp:journals/kais/KoKJS25