Learning from aggregated data with a maximum entropy model - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

Learning from aggregated data with a maximum entropy model

Alexandre Gilotte
  • Function : Author
Ahmed Ben Yamed
  • Function : Author
  • PersonId : 1161754
David Rohde
  • Function : Author
  • PersonId : 1053680


Aggregating a dataset, then injecting some noise, is a simple and common way to release differentially private data. However, aggregated data -even without noise- is not an appropriate input for machine learning classifiers. In this work, we show how a new model, similar to a logistic regression, may be learned from aggregated data only by approximating the unobserved feature distribution with a maximum entropy hypothesis. The resulting model is a Markov Random Field (MRF), and we detail how to apply, modify and scale a MRF training algorithm to our setting. Finally we present empirical evidence on several public datasets that the model learned this way can achieve performances comparable to those of a logistic model trained with the full unaggregated data.
Fichier principal
Vignette du fichier
aggregates.pdf (594.24 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03770740 , version 1 (06-09-2022)
hal-03770740 , version 2 (04-10-2022)


  • HAL Id : hal-03770740 , version 2
  • ARXIV : 3796293


Alexandre Gilotte, Ahmed Ben Yamed, David Rohde. Learning from aggregated data with a maximum entropy model. 2022. ⟨hal-03770740v2⟩
32 View
76 Download



Gmail Facebook Twitter LinkedIn More