On the Out-of-Distribution Evaluation of ML-Based End-to-End Communications Systems
Bibliographic record
Abstract
Machine learning (ML)-aided wireless communication studies are initiating the investigation of the domain generalization capabilities of deep neural networks (DNNs) when applied to communication problems. They do so by adopting the out-of-distribution (OOD) performance evaluation by comparing it to the in-distribution (ID) performance as usually done within the ML community. In this paper, we demonstrate that such blind adoption can yield a misleading OOD performance analysis of DNNs unless wireless communication metrics are involved in the OOD evaluation. By analyzing the OOD performance of an end-to-end (E2E) ML communication system over additive white Gaussian noise (AWGN) channels in terms of bit error rate (BER), we show that smaller (resp. larger) BER gaps between ID and OOD performance do not necessarily translate into a high (resp. low) reconstruction accuracy. Our results suggest that the comparison between ID and OOD performances is not enough to judge whether the OOD performance is acceptable or not. The ID and OOD performances of E2E communication systems should instead be carried out based on wireless metrics.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".