Influence Estimation for Generative Adversarial Networks
- URL: http://arxiv.org/abs/2101.08367v1
- Date: Wed, 20 Jan 2021 23:55:54 GMT
- Title: Influence Estimation for Generative Adversarial Networks
- Authors: Naoyuki Terashita, Hiroki Ohashi, Yuichi Nonaka, Takashi Kanemaru
- Abstract summary: Previous approaches require that the absence of a training instance directly affects the loss value.
We propose a novel evaluation scheme, in which we assess harmfulness of each training instance on the basis of how GAN evaluation metric is expect to change.
- Score: 0.4014524824655105
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Identifying harmful instances, whose absence in a training dataset improves
model performance, is important for building better machine learning models.
Although previous studies have succeeded in estimating harmful instances under
supervised settings, they cannot be trivially extended to generative
adversarial networks (GANs). This is because previous approaches require that
(1) the absence of a training instance directly affects the loss value and that
(2) the change in the loss directly measures the harmfulness of the instance
for the performance of a model. In GAN training, however, neither of the
requirements is satisfied. This is because, (1) the generator's loss is not
directly affected by the training instances as they are not part of the
generator's training steps, and (2) the values of GAN's losses normally do not
capture the generative performance of a model. To this end, (1) we propose an
influence estimation method that uses the Jacobian of the gradient of the
generator's loss with respect to the discriminator's parameters (and vice
versa) to trace how the absence of an instance in the discriminator's training
affects the generator's parameters, and (2) we propose a novel evaluation
scheme, in which we assess harmfulness of each training instance on the basis
of how GAN evaluation metric (e.g., inception score) is expect to change due to
the removal of the instance. We experimentally verified that our influence
estimation method correctly inferred the changes in GAN evaluation metrics.
Further, we demonstrated that the removal of the identified harmful instances
effectively improved the model's generative performance with respect to various
GAN evaluation metrics.
Related papers
- Data Cleansing for GANs [12.466874710578612]
One effective strategy that applies to any machine learning task is identifying harmful instances, whose removal improves the performance.
Previous approaches require that the absence of a training instance directly affects the parameters.
We propose an instance evaluation scheme that measures the harmfulness of each training instance based on how a GAN evaluation metric is expected to change by the instance's removal.
arXiv Detail & Related papers (2025-04-01T10:02:37Z) - Individualized Policy Evaluation and Learning under Clustered Network
Interference [4.560284382063488]
We consider the problem of evaluating and learning an optimal individualized treatment rule under clustered network interference.
We propose an estimator that can be used to evaluate the empirical performance of an ITR.
We derive the finite-sample regret bound for a learned ITR, showing that the use of our efficient evaluation estimator leads to the improved performance of learned policies.
arXiv Detail & Related papers (2023-11-04T17:58:24Z) - Time-series Generation by Contrastive Imitation [87.51882102248395]
We study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy.
At inference, the learned policy serves as the generator for iterative sampling, and the learned energy serves as a trajectory-level measure for evaluating sample quality.
arXiv Detail & Related papers (2023-11-02T16:45:25Z) - Adapt then Unlearn: Exploiting Parameter Space Semantics for Unlearning
in Generative Adversarial Networks [5.479797073162603]
This work is inspired by a crucial observation: the parameter space of GANs exhibits meaningful directions that can be leveraged to suppress specific undesired features.
Our proposed method, known as 'Adapt-then-Unlearn,' excels at unlearning such undesirable features while also maintaining the quality of generated samples.
This method unfolds in two stages: in the initial stage, we adapt the pre-trained GAN using negative samples provided by the user, while in the subsequent stage, we focus on unlearning the undesired feature.
arXiv Detail & Related papers (2023-09-25T11:36:20Z) - Augmentation-Aware Self-Supervision for Data-Efficient GAN Training [68.81471633374393]
Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting.
We propose a novel augmentation-aware self-supervised discriminator that predicts the augmentation parameter of the augmented data.
We compare our method with state-of-the-art (SOTA) methods using the class-conditional BigGAN and unconditional StyleGAN2 architectures.
arXiv Detail & Related papers (2022-05-31T10:35:55Z) - Monitoring Model Deterioration with Explainable Uncertainty Estimation
via Non-parametric Bootstrap [0.0]
Monitoring machine learning models once they are deployed is challenging.
It is even more challenging to decide when to retrain models in real-case scenarios when labeled data is beyond reach.
In this work, we use non-parametric bootstrapped uncertainty estimates and SHAP values to provide explainable uncertainty estimation.
arXiv Detail & Related papers (2022-01-27T17:23:04Z) - Efficient Estimation of Influence of a Training Instance [56.29080605123304]
We propose an efficient method for estimating the influence of a training instance on a neural network model.
Our method is inspired by dropout, which zero-masks a sub-network and prevents the sub-network from learning each training instance.
We demonstrate that the proposed method can capture training influences, enhance the interpretability of error predictions, and cleanse the training dataset for improving generalization.
arXiv Detail & Related papers (2020-12-08T04:31:38Z) - Estimating Generalization under Distribution Shifts via Domain-Invariant
Representations [75.74928159249225]
We use a set of domain-invariant predictors as a proxy for the unknown, true target labels.
The error of the resulting risk estimate depends on the target risk of the proxy model.
arXiv Detail & Related papers (2020-07-06T17:21:24Z) - How Training Data Impacts Performance in Learning-based Control [67.7875109298865]
This paper derives an analytical relationship between the density of the training data and the control performance.
We formulate a quality measure for the data set, which we refer to as $rho$-gap.
We show how the $rho$-gap can be applied to a feedback linearizing control law.
arXiv Detail & Related papers (2020-05-25T12:13:49Z) - Learning to Predict Error for MRI Reconstruction [67.76632988696943]
We demonstrate that predictive uncertainty estimated by the current methods does not highly correlate with prediction error.
We propose a novel method that estimates the target labels and magnitude of the prediction error in two steps.
arXiv Detail & Related papers (2020-02-13T15:55:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.