TRUST-ADAPT: Risk-Gated Reversible Test-Time Learning with Conformal Shift Evidence and Selective Memory

Prudvi Saisaran Ponduru, Pavani Priya Vyshnavi Nandanavanam and Sai Kesav Kumar Ponduru

International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2025, vol. 11, issue 2, 4011-4028

Abstract: Test-time adaptation (TTA) can improve predictions after deployment, but the update itself can become a new failure mode when unlabeled streams are transient, contaminated, imbalanced, or recurrent. We introduce TRUST-ADAPT, a risk-gated TTA algorithm that treats adaptation as a reversible intervention rather than a default response. A frozen source model converts confidence nonconformity into split-conformal p-values; a batch-level Hoeffding gate triggers learning only when the fraction of anomalous samples exceeds a finite-sample threshold. Triggered batches are further filtered by predictive uncertainty, adapted with pseudo-label and entropy objectives regularized by an immutable source anchor and selective class-balanced memory, and accepted only if an anchor-risk validation check passes; otherwise the parameters are rolled back. Under super-uniform conformal p-values and conditional within-batch independence, the gate controls the probability of a false adaptation trigger at a user-specified level. We implement the complete procedure in PyTorch and execute a locked five-seed controlled benchmark on streaming digit classification with abrupt, recurring, and 15% contaminated shifts. Across 15 seed-scenario pairs, TRUST-ADAPT improves mean streaming accuracy over the frozen source by 3.20 percentage points (Holm-adjusted Wilcoxon p=0.0039) while using 49.8 update batches on average versus 90.0 for TENT-style adaptation. The method is particularly competitive under contamination, but recurring shifts remain a limitation. All reported values are generated by the accompanying executable code; no unexecuted numerical result is claimed.

Keywords: conformal prediction; continual adaptation; distribution shift; selective memory; test-time adaptation; uncertainty (search for similar items in EconPapers)
Date: 2025
Note: Article URL: https://ijsrcseit.com/home/article/view/CSEIT25113445
References: Add references at CitEc
Citations:

Downloads: (external link)
https://ijsrcseit.com/home/article/view/CSEIT25113445 Article URL (text/html)
https://ijsrcseit.com/home/article/download/CSEIT25113445/CSEIT25113445 Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:jbh:ijsrcs:v11:y2025:i2:id:2156

DOI: 10.32628/CSEIT25113445

Access Statistics for this article

More articles in International Journal of Scientific Research in Computer Science, Engineering and Information Technology from International Journal of Scientific Research in Computer Science, Engineering and Information Technology
Bibliographic data for series maintained by Pankaj Sharma ().