SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.20082 · NeurIPS · 2024

Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series Representations

Ali Etemad, Shivam Grover, Amin Jalali

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
shivam-grover/s3-timeseries canonical 0 of 2
FunctionStatusWhere it lives
S3Layer Not yet run shivam-grover/s3-timeseries/S3/S3.py
code served (permissive licence) · get_code("267fa662c6f7f5c5")
objective Not yet run shivam-grover/s3-timeseries/example/grid_search_template.py
code served (permissive licence) · get_code("5e38e239bde01c7c")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Existing approaches for learning representations of time-series keep the temporal arrangement of the time-steps intact with the presumption that the original order is the most optimal for learning. However, non-adjacent sections of real-world time-series may have strong dependencies. Accordingly, we raise the question: Is there an alternative arrangement for time-series which could enable more effective representation learning? To address this, we propose a simple plug-andplay neural network layer called Segment, Shuffle, and Stitch (S3) designed to improve representation learning in time-series models. S3 works by creating nonoverlapping segments from the original sequence and shuffling them in a learned manner that is optimal for the task at hand. It then re-attaches the shuffled segments back together and performs a learned weighted sum with the original input to capture both the newly shuffled sequence along with the original sequence. S3 is modular and can be stacked to achieve different levels of granularity, and can be added to many forms of neural architectures including CNNs or Transformers with negligible computation overhead. Through extensive experiments on several datasets and state-of-the-art baselines, we show that incorporating S3 results in significant improvements for the tasks of time-series classification, forecasting, and anomaly detection, improving performance on certain datasets by up to 68%. We also show that S3 makes the learning more stable with a smoother training loss curve and loss landscape compared to the original baseline. The code is available at https://github.com/shivam-grover/S3-TimeSeries.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2405.20082")
get_code_for_paper("2405.20082")
have("2405.20082")

Connect an agent — have() is free.