Unsupervised Representation Learning for Time Series with Temporal\n Neighborhood Coding
Bibliographic record
Abstract
Time series are often complex and rich in information but sparsely labeled\nand therefore challenging to model. In this paper, we propose a self-supervised\nframework for learning generalizable representations for non-stationary time\nseries. Our approach, called Temporal Neighborhood Coding (TNC), takes\nadvantage of the local smoothness of a signal's generative process to define\nneighborhoods in time with stationary properties. Using a debiased contrastive\nobjective, our framework learns time series representations by ensuring that in\nthe encoding space, the distribution of signals from within a neighborhood is\ndistinguishable from the distribution of non-neighboring signals. Our\nmotivation stems from the medical field, where the ability to model the dynamic\nnature of time series data is especially valuable for identifying, tracking,\nand predicting the underlying patients' latent states in settings where\nlabeling data is practically impossible. We compare our method to recently\ndeveloped unsupervised representation learning approaches and demonstrate\nsuperior performance on clustering and classification tasks for multiple\ndatasets.\n
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".