Adversarial Learning

Summary

AMF.AMF.AMF(data, config, params, *args, …)

Adversarial Matrix Factorization

AMR.AMR.AMR(data, config, params, *args, …)

Adversarial Multimedia Recommender

AMF

class elliot.recommender.adversarial.AMF.AMF.AMF(data, config, params, *args, **kwargs)[source]

Bases: elliot.recommender.recommender_utils_mixin.RecMixin, elliot.recommender.base_recommender_model.BaseRecommenderModel

Adversarial Matrix Factorization

For model details, please refer to the paper

The model support two adversarial perturbations methods:

FGSM-based presented by X. He et al in paper <https://arxiv.org/abs/1808.03908>

MSAP presented by Anelli et al. in paper <https://journals.flvc.org/FLAIRS/article/view/128443>

Parameters

  • meta – eval_perturbations: If True Elliot evaluates the effects of both FGSM and MSAP perturbations for each validation epoch

  • factors – Number of latent factor

  • lr – Learning rate

  • l_w – Regularization coefficient

  • l_b – Regularization coefficient of bias

  • eps – Perturbation Budget

  • l_adv – Adversarial regularization coefficient

  • adversarial_epochs – Adversarial epochs

  • eps_iter – Size of perturbations in MSAP perturbations

  • nb_iter – Number of Iterations in MSAP perturbations

To include the recommendation model, add it to the config file adopting the following pattern:

models:
  AMF:
    meta:
      save_recs: True
      eval_perturbations: True
    epochs: 10
    batch_size: 512
    factors: 200
    lr: 0.001
    l_w: 0.1
    l_b: 0.001
    eps: 0.1
    l_adv: 0.001
    adversarial_epochs: 10
    nb_iter: 20
    eps_iter: 0.00001  # If not specified = 2.5*eps/nb_iter

AMR

class elliot.recommender.adversarial.AMR.AMR.AMR(data, config, params, *args, **kwargs)[source]

Bases: elliot.recommender.recommender_utils_mixin.RecMixin, elliot.recommender.base_recommender_model.BaseRecommenderModel

Adversarial Multimedia Recommender

For further details, please refer to the paper

The model support two adversarial perturbations methods:

FGSM-based presented by X. He et al in paper <https://arxiv.org/pdf/1809.07062.pdf>

MSAP presented by Anelli et al. in paper <https://journals.flvc.org/FLAIRS/article/view/128443>

Parameters

  • meta – eval_perturbations: If True Elliot evaluates the effects of both FGSM and MSAP perturbations for each validation epoch

  • factors – Number of latent factor

  • factors_d – Image-feature dimensionality

  • lr – Learning rate

  • l_w – Regularization coefficient

  • l_b – Regularization coefficient of bias

  • l_e – Regularization coefficient of image matrix embedding

  • eps – Perturbation Budget

  • l_adv – Adversarial regularization coefficient

  • adversarial_epochs – Adversarial epochs

  • eps_iter – Size of perturbations in MSAP perturbations

  • nb_iter – Number of Iterations in MSAP perturbations

To include the recommendation model, add it to the config file adopting the following pattern:

models:
  AMR:
    meta:
      save_recs: True
      eval_perturbations: True
    epochs: 10
    batch_size: 512
    factors: 200
    factors_d: 20
    lr: 0.001
    l_w: 0.1
    l_b: 0.001
    l_e: 0.1
    eps: 0.1
    l_adv: 0.001
    adversarial_epochs: 5
    eps_iter: 0.00001
    nb_iter: 20
    nb_iter: 20
    eps_iter: 0.00001  # If not specified = 2.5*eps/nb_iter