Semi-Supervised Federated Analytics for Heterogeneous Household Characteristics Identification
Bibliographic record
Abstract
The widespread use of smart meters in households paves the way for retailers to understand household patterns through electricity usage data. This insight helps them offer personalized services and create better demand response strategies. However, smart meter data is highly heterogeneous since it is collected by different retailers using various data sampling methods, over different time periods, and from households with distinct characteristics. Additionally, the labels of household characteristics are obtained by questionnaires, which is labor-intensive and time-consuming, leaving much data unlabeled while privacy concerns prevent data sharing among retailers. To address these challenges, we propose a novel Semi-Supervised Federated Analytics approach for Heterogeneous Smart Meter Data (SF-Heter). This method keeps raw data local and exchanges analytics outputs, called prototypes, between retailers and a central server, thus dealing with heterogeneous data and protecting privacy. SF-Heter utilizes a new model structure named MODlinear, which enhances feature extraction through contrastive learning and multi-kernel time-series analysis. Meanwhile, SF-Heter efficiently utilizes unlabeled data by generating high-quality pseudo-labels and prototypes using MODlinear and integrated with a quality-controlled semi-supervised loss mechanism. Extensive tests on the Irish dataset show that SF-Heter effectively handles data heterogeneity and optimizes the use of unlabeled data.
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 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| 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".