SamBaTen: Sampling-based Batch Incremental Tensor Decomposition
This addresses the challenge of efficiently updating tensor decompositions for large-scale, evolving datasets in fields like online social networks, offering a scalable solution where prior incremental methods fail.
The paper tackles the problem of maintaining accurate tensor decompositions for dynamically evolving multimodal datasets without recomputing from scratch, introducing SaMbaTen, which achieves comparable accuracy to state-of-the-art methods while being 25-30 times faster and scaling to tensors up to 100K x 100K x 100K dimensions.
Tensor decompositions are invaluable tools in analyzing multimodal datasets. In many real-world scenarios, such datasets are far from being static, to the contrary they tend to grow over time. For instance, in an online social network setting, as we observe new interactions over time, our dataset gets updated in its "time" mode. How can we maintain a valid and accurate tensor decomposition of such a dynamically evolving multimodal dataset, without having to re-compute the entire decomposition after every single update? In this paper we introduce SaMbaTen, a Sampling-based Batch Incremental Tensor Decomposition algorithm, which incrementally maintains the decomposition given new updates to the tensor dataset. SaMbaTen is able to scale to datasets that the state-of-the-art in incremental tensor decomposition is unable to operate on, due to its ability to effectively summarize the existing tensor and the incoming updates, and perform all computations in the reduced summary space. We extensively evaluate SaMbaTen using synthetic and real datasets. Indicatively, SaMbaTen achieves comparable accuracy to state-of-the-art incremental and non-incremental techniques, while being 25-30 times faster. Furthermore, SaMbaTen scales to very large sparse and dense dynamically evolving tensors of dimensions up to 100K x 100K x 100K where state-of-the-art incremental approaches were not able to operate.