FLightNER: A Federated Learning Approach to Lightweight Named-Entity Recognition
Bibliographic record
Abstract
We introduce FLightNER, a Federated Learning (FL) model that extends an existing state-of-the-art Named-Entity Recognition (NER) model using prompt-tuning known as LightNER. FLightNER allows the aggregation of only the trainable parameters of LightNER without model accuracy degradation saving 10 GB per client enabling more clients to join a federation without extending the central server’s memory. We evaluate our approach against two baselines using three diverse datasets with different distributions across up to seven clients in a federation. We empirically show that compared to the centrally-trained LightNER model, FLightNER outperforms it by 19% when performed on a medical dataset with label imbalance across clients and matches it when performed on two balanced datasets: CoNLL and I2B2. Furthermore, we use and evaluate two well-established memory-saving techniques: AdaFactor optimizer and Automatic Mixed Precision on our FL approach. Our findings enable owners of sensitive data such as healthcare practitioners to efficiently train an NER model collaboratively, with low memory requirements, while keeping their data on-premise.
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 | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.006 |
| Open science | 0.004 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.003 |
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".