Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userHydra: Preserving Ensemble Diversity for Model Distillation
77
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
Ensembles of models have been empirically shown to improve predictive performance and to yield robust measures of uncertainty. However, they are expensive in computation and memory. Therefore, recent research has focused on distilling ensembles into a single compact model, reducing the computational and memory burden of the ensemble while trying to preserve its predictive behavior. Most existing distillation formulations summarize the ensemble by capturing its average predictions. As a result, the diversity of the ensemble predictions, stemming from each member, is lost. Thus, the distilled model cannot provide a measure of uncertainty comparable to that of the original ensemble. To retain more faithfully the diversity of the ensemble, we propose a distillation method based on a single multi-headed neural network, which we refer to as Hydra. The shared body network learns a joint feature representation that enables each head to capture the predictive behavior of each ensemble member. We demonstrate that with a slight increase in parameter count, Hydra improves distillation performance on classification and regression settings while capturing the uncertainty behavior of the original ensemble over both in-domain and out-of-distribution tasks.
rate research
Read More
Though deep neural networks have achieved significant progress on various tasks, often enhanced by model ensemble, existing high-performance models can be vulnerable to adversarial attacks. Many efforts have been devoted to enhancing the robustness of individual networks and then constructing a straightforward ensemble, e.g., by directly averaging the outputs, which ignores the interaction among networks. This paper presents a new method that explores the interaction among individual networks to improve robustness for ensemble models. Technically, we define a new notion of ensemble diversity in the adversarial setting as the diversity among non-maximal predictions of individual members, and present an adaptive diversity promoting (ADP) regularizer to encourage the diversity, which leads to globally better robustness for the ensemble by making adversarial examples difficult to transfer among individual members. Our method is computationally efficient and compatible with the defense methods acting on individual networks. Empirical results on various datasets verify that our method can improve adversarial robustness while maintaining state-of-the-art accuracy on normal examples.
Ensemble learning is a methodology that integrates multiple DNN learners for improving prediction performance of individual learners. Diversity is greater when the errors of the ensemble prediction is more uniformly distributed. Greater diversity is highly correlated with the increase in ensemble accuracy. Another attractive property of diversity optimized ensemble learning is its robustness against deception: an adversarial perturbation attack can mislead one DNN model to misclassify but may not fool other ensemble DNN members consistently. In this paper we first give an overview of the concept of ensemble diversity and examine the three types of ensemble diversity in the context of DNN classifiers. We then describe a set of ensemble diversity measures, a suite of algorithms for creating diversity ensembles and for performing ensemble consensus (voted or learned) for generating high accuracy ensemble output by strategically combining outputs of individual members. This paper concludes with a discussion on a set of open issues in quantifying ensemble diversity for robust deep learning.
Predicting user positive response (e.g., purchases and clicks) probability is a critical task in Web applications. To identify predictive features from raw data, the state-of-the-art extreme deep factorization machine (xDeepFM) model introduces a compressed interaction network (CIN) to leverage feature interactions at the vector-wise level explicitly. However, since each hidden layer in CIN is a collection of feature maps, it can be viewed essentially as an ensemble of different feature maps. In this case, only using a single objective to minimize the prediction loss may lead to overfitting. In this paper, an ensemble diversity enhanced extreme deep factorization machine model (DexDeepFM) is proposed, which introduces the ensemble diversity measure in CIN and considers both ensemble diversity and prediction accuracy in the objective function. In addition, the attention mechanism is introduced to discriminate the importance of ensemble diversity measures with different feature interaction orders. Extensive experiments on two public real-world datasets show the superiority of the proposed model.
Adversarial Transferability is an intriguing property of adversarial examples -- a perturbation that is crafted against one model is also effective against another model, which may arise from a different model family or training process. To better protect ML systems against adversarial attacks, several questions are raised: what are the sufficient conditions for adversarial transferability? Is it possible to bound such transferability? Is there a way to reduce the transferability in order to improve the robustness of an ensemble ML model? To answer these questions, we first theoretically analyze sufficient conditions for transferability between models and propose a practical algorithm to reduce transferability within an ensemble to improve its robustness. Our theoretical analysis shows only the orthogonality between gradients of different models is not enough to ensure low adversarial transferability: the model smoothness is also an important factor. In particular, we provide a lower/upper bound of adversarial transferability based on model gradient similarity for low risk classifiers based on gradient orthogonality and model smoothness. We demonstrate that under the condition of gradient orthogonality, smoother classifiers will guarantee lower adversarial transferability. Furthermore, we propose an effective Transferability Reduced Smooth-ensemble(TRS) training strategy to train a robust ensemble with low transferability by enforcing model smoothness and gradient orthogonality between base models. We conduct extensive experiments on TRS by comparing with other state-of-the-art baselines on different datasets, showing that the proposed TRS outperforms all baselines significantly. We believe our analysis on adversarial transferability will inspire future research towards developing robust ML models taking these adversarial transferability properties into account.
We formally study how ensemble of deep learning models can improve test accuracy, and how the superior performance of ensemble can be distilled into a single model using knowledge distillation. We consider the challenging case where the ensemble is simply an average of the outputs of a few independently trained neural networks with the SAME architecture, trained using the SAME algorithm on the SAME data set, and they only differ by the random seeds used in the initialization. We empirically show that ensemble/knowledge distillation in deep learning works very differently from traditional learning theory, especially differently from ensemble of random feature mappings or the neural-tangent-kernel feature mappings, and is potentially out of the scope of existing theorems. Thus, to properly understand ensemble and knowledge distillation in deep learning, we develop a theory showing that when data has a structure we refer to as multi-view, then ensemble of independently trained neural networks can provably improve test accuracy, and such superior test accuracy can also be provably distilled into a single model by training a single model to match the output of the ensemble instead of the true label. Our result sheds light on how ensemble works in deep learning in a way that is completely different from traditional theorems, and how the dark knowledge is hidden in the outputs of the ensemble -- that can be used in knowledge distillation -- comparing to the true data labels. In the end, we prove that self-distillation can also be viewed as implicitly combining ensemble and knowledge distillation to improve test accuracy.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
