اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدDoes Adversarial Oversampling Help us?
74
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Traditional oversampling methods are generally employed to handle class imbalance in datasets. This oversampling approach is independent of the classifier; thus, it does not offer an end-to-end solution. To overcome this, we propose a three-player adversarial game-based end-to-end method, where a domain-constraints mixture of generators, a discriminator, and a multi-class classifier are used. Rather than adversarial minority oversampling, we propose an adversarial oversampling (AO) and a data-space oversampling (DO) approach. In AO, the generator updates by fooling both the classifier and discriminator, however, in DO, it updates by favoring the classifier and fooling the discriminator. While updating the classifier, it considers both the real and synthetically generated samples in AO. But, in DO, it favors the real samples and fools the subset class-specific generated samples. To mitigate the biases of a classifier towards the majority class, minority samples are over-sampled at a fractional rate. Such implementation is shown to provide more robust classification boundaries. The effectiveness of our proposed method has been validated with high-dimensional, highly imbalanced and large-scale multi-class tabular datasets. The results as measured by average class specific accuracy (ACSA) clearly indicate that the proposed method provides better classification accuracy (improvement in the range of 0.7% to 49.27%) as compared to the baseline classifier.
قيم البحث
اقرأ أيضاً
In Newcombs paradox you choose to receive either the contents of a particular closed box, or the contents of both that closed box and another one. Before you choose, a prediction algorithm deduces your choice, and fills the two boxes based on that de
duction. Newcombs paradox is that game theory appears to provide two conflicting recommendations for what choice you should make in this scenario. We analyze Newcombs paradox using a recent extension of game theory in which the players set conditional probability distributions in a Bayes net. We show that the two game theory recommendations in Newcombs scenario have different presumptions for what Bayes net relates your choice and the algorithms prediction. We resolve the paradox by proving that these two Bayes nets are incompatible. We also show that the accuracy of the algorithms prediction, the focus of much previous work, is irrelevant. In addition we show that Newcombs scenario only provides a contradiction between game theorys expected utility and dominance principles if one is sloppy in specifying the underlying Bayes net. We also show that Newcombs paradox is time-reversal invariant; both the paradox and its resolution are unchanged if the algorithm makes its `prediction after you make your choice rather than before.
Face occlusions, covering either the majority or discriminative parts of the face, can break facial perception and produce a drastic loss of information. Biometric systems such as recent deep face recognition models are not immune to obstructions or
other objects covering parts of the face. While most of the current face recognition methods are not optimized to handle occlusions, there have been a few attempts to improve robustness directly in the training stage. Unlike those, we propose to study the effect of generative face completion on the recognition. We offer a face completion encoder-decoder, based on a convolutional operator with a gating mechanism, trained with an ample set of face occlusions. To systematically evaluate the impact of realistic occlusions on recognition, we propose to play the occlusion game: we render 3D objects onto different face parts, providing precious knowledge of what the impact is of effectively removing those occlusions. Extensive experiments on the Labeled Faces in the Wild (LFW), and its more difficult variant LFW-BLUFR, testify that face completion is able to partially restore face perception in machine vision systems for improved recognition.
Mixup is a popular data augmentation technique based on taking convex combinations of pairs of examples and their labels. This simple technique has been shown to substantially improve both the robustness and the generalization of the trained model. H
owever, it is not well-understood why such improvement occurs. In this paper, we provide theoretical analysis to demonstrate how using Mixup in training helps model robustness and generalization. For robustness, we show that minimizing the Mixup loss corresponds to approximately minimizing an upper bound of the adversarial loss. This explains why models obtained by Mixup training exhibits robustness to several kinds of adversarial attacks such as Fast Gradient Sign Method (FGSM). For generalization, we prove that Mixup augmentation corresponds to a specific type of data-adaptive regularization which reduces overfitting. Our analysis provides new insights and a framework to understand Mixup.
Weight sharing, as an approach to speed up architecture performance estimation has received wide attention. Instead of training each architecture separately, weight sharing builds a supernet that assembles all the architectures as its submodels. Howe
ver, there has been debate over whether the NAS process actually benefits from weight sharing, due to the gap between supernet optimization and the objective of NAS. To further understand the effect of weight sharing on NAS, we conduct a comprehensive analysis on five search spaces, including NAS-Bench-101, NAS-Bench-201, DARTS-CIFAR10, DARTS-PTB, and ProxylessNAS. We find that weight sharing works well on some search spaces but fails on others. Taking a step forward, we further identified biases accounting for such phenomenon and the capacity of weight sharing. Our work is expected to inspire future NAS researchers to better leverage the power of weight sharing.
We investigate whether Jacobi preconditioning, accounting for the bootstrap term in temporal difference (TD) learning, can help boost performance of adaptive optimizers. Our method, TDprop, computes a per parameter learning rate based on the diagonal
preconditioning of the TD update rule. We show how this can be used in both $n$-step returns and TD($lambda$). Our theoretical findings demonstrate that including this additional preconditioning information is, surprisingly, comparable to normal semi-gradient TD if the optimal learning rate is found for both via a hyperparameter search. In Deep RL experiments using Expected SARSA, TDprop meets or exceeds the performance of Adam in all tested games under near-optimal learning rates, but a well-tuned SGD can yield similar improvements -- matching our theory. Our findings suggest that Jacobi preconditioning may improve upon typical adaptive optimization methods in Deep RL, but despite incorporating additional information from the TD bootstrap term, may not always be better than SGD.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
