Deep learning is often criticized by two serious issues which rarely exist in natural nervous systems: overfitting and catastrophic forgetting. It can even memorize randomly labelled data, which has little knowledge behind the instance-label pairs. When a deep network continually learns over time by accommodating new tasks, it usually quickly overwrites the knowledge learned from previous tasks. Referred to as the {\it neural variability}, it is well-known in neuroscience that human brain reactions exhibit substantial variability even in response to the same stimulus. This mechanism balances accuracy and plasticity/flexibility in the motor learning of natural nervous systems. Thus it motivates us to design a similar mechanism named {\it artificial neural variability} (ANV), which helps artificial neural networks learn some advantages from ``natural'' neural networks. We rigorously prove that ANV plays as an implicit regularizer of the mutual information between the training data and the learned model. This result theoretically guarantees ANV a strictly improved generalizability, robustness to label noise, and robustness to catastrophic forgetting. We then devise a {\it neural variable risk minimization} (NVRM) framework and {\it neural variable optimizers} to achieve ANV for conventional network architectures in practice. The empirical studies demonstrate that NVRM can effectively relieve overfitting, label noise memorization, and catastrophic forgetting at negligible costs. \footnote{Code: \url{https://github.com/zeke-xie/artificial-neural-variability-for-deep-learning}.
Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Swiss Federal Institute of Technology in Lausanne (EPFL)（洛桑联邦理工学院）
The ability to quickly learn new knowledge (e.g. new classes or data distributions) is a big step towards human-level intelligence. In this paper, we consider scenarios that require learning new classes or data distributions quickly and incrementally over time, as it often occurs in real-world dynamic environments. We propose "Memory-based Hebbian Parameter Adaptation" (Hebb) to tackle the two major challenges (i.e., catastrophic forgetting and sample efficiency) towards this goal in a unified framework. To mitigate catastrophic forgetting, Hebb augments a regular neural classifier with a cont…
In this paper we propose to study generalization of neural networks on small algorithmically generated datasets. In this setting, questions about data efficiency, memorization, generalization, and speed of learning can be studied in great detail. In some situations we show that neural networks learn through a process of "grokking" a pattern in the data, improving generalization performance from random chance level to perfect generalization, and that this improvement in generalization can happen well past the point of overfitting. We also study generalization as a function of dataset size and f…
Hong Kong Baptist University（香港浸会大学）；RIKEN（理化学研究所）；AAII, University of Technology Sydney（悉尼科技大学人工智能研究所）；Paradigm Inc. (Hong Kong)（第四范式（香港））；University of Queensland（昆士兰大学）；The University of Tokyo（东京大学）
Given data with noisy labels, over-parameterized deep networks can gradually memorize the data, and fit everything in the end. Although equipped with corrections for noisy labels, many learning methods in this area still suffer overfitting due to undesired memorization. In this paper, to relieve this issue, we propose stochastic integrated gradient underweighted ascent (SIGUA): in a mini-batch, we adopt gradient descent on good data as usual, and learning-rate-reduced gradient ascent on bad data; the proposal is a versatile approach where data goodness or badness is w.r.t. desired or undesired…
Applicability of memorization indicators for early spotting of overfitting while recalibrating sEMG-decoders on low sample sizes
German Aerospace Center (DLR), Institute for AI Safety and Security（德国航空航天中心（DLR），人工智能安全与安全研究所）；Faculty of Electrical Engineering and Information Technology, Ruhr University Bochum（波鸿鲁尔大学电气工程与信息技术学院）；Institute for Neural Computation, Ruhr University Bochum（波鸿鲁尔大学神经计算研究所）；Institute of Computer Science, Ruhr West University of Applied Science（鲁尔西部应用科学大学计算机科学研究所）
Deep Neural Networks, often owing to the overparameterization, are shown to be capable of exactly memorizing even randomly labelled data. Empirical studies have also shown that none of the standard regularization techniques mitigate such overfitting. We investigate whether the choice of the loss function can affect this memorization. We empirically show, with benchmark data sets MNIST and CIFAR-10, that a symmetric loss function, as opposed to either cross-entropy or squared error loss, results in significant improvement in the ability of the network to resist such overfitting. We then provide…
Don't Forget! Decomposing the Training Dynamics of Memorization in Language Models
LMU Munich（慕尼黑大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Mila – Quebec AI Institute（魁北克人工智能研究所）；University of Montreal（蒙特利尔大学）；Saarland University（萨尔大学）
RMIT University（皇家墨尔本理工大学）；University of Technology Sydney（悉尼科技大学）；Griffith University（格里菲斯大学）；Data61, CSIRO（联邦科学与工业研究组织Data61）；Swinburne University of Technology（斯威本科技大学）
Undetected overfitting can occur when there are significant redundancies between training and validation data. We describe AVE, a new measure of training-validation redundancy for ligand-based classification problems that accounts for the similarity amongst inactive molecules as well as active. We investigated seven widely-used benchmarks for virtual screening and classification, and show that the amount of AVE bias strongly correlates with the performance of ligand-based predictive methods irrespective of the predicted property, chemical fingerprint, similarity measure, or previously-applied …
Deep learning models have a propensity for fitting the entire training set even with random labels, which requires memorization of every training sample. In this paper, we explore the memorization effect in adversarial training (AT) for promoting a deeper understanding of model capacity, convergence, generalization, and especially robust overfitting of the adversarially trained models. We first demonstrate that deep networks have sufficient capacity to memorize adversarial examples of training data with completely random labels, but not all AT algorithms can converge under the extreme circumst…
University of California, Santa Cruz（加州大学圣克鲁兹分校）；Tencent YouTu Lab（腾讯优图实验室）
Designing robust loss functions is popular in learning with noisy labels while existing designs did not explicitly consider the overfitting property of deep neural networks (DNNs). As a result, applying these losses may still suffer from overfitting/memorizing noisy labels as training proceeds. In this paper, we first theoretically analyze the memorization effect and show that a lower-capacity model may perform better on noisy datasets. However, it is non-trivial to design a neural network with the best capacity given an arbitrary task. To circumvent this dilemma, instead of changing the model…
Very large deep learning models trained using gradient descent are remarkably resistant to memorization given their huge capacity, but are at the same time capable of fitting large datasets of pure noise. Here methods are introduced by which models may be trained to memorize datasets that normally are generalized. We find that memorization is difficult relative to generalization, but that adding noise makes memorization easier. Increasing the dataset size exaggerates the characteristics of that dataset: model access to more training samples makes overfitting easier for random data, but somewha…
Despite the empirical advances of deep learning across a variety of learning tasks, our theoretical understanding of its success is still very restricted. One of the key challenges is the overparametrized nature of modern models, enabling complete overfitting of the data even if the labels are randomized, i.e. networks can completely \textit{memorize} all given patterns. While such a memorization capacity seems worrisome, in this work we show that under training protocols that include \textit{data augmentation}, neural networks learn to memorize entirely random labels in a benign way, i.e. the…
Normandie Univ（诺曼底大学）；UNICAEN（卡昂大学）；ENSICAEN（卡昂高等工程师学院）；CNRS — UMR GREYC（法国国家科学研究中心 — 灰谐实验室联合研究单位（注：CNRS为法国国家科学研究中心，UMR为联合研究单位缩写，GREYC为实验室名，此处按原文提取机构部分））
State of the art deep generative networks are capable of producing images with such incredible realism that they can be suspected of memorizing training images. It is why it is not uncommon to include visualizations of training set nearest neighbors, to suggest generated images are not simply memorized. We demonstrate this is not sufficient and motivates the need to study memorization/overfitting of deep generators with more scrutiny. This paper addresses this question by i) showing how simple losses are highly effective at reconstructing images for deep generators ii) analyzing the statistics…
The Alan Turing Institute（艾伦·图灵研究所）；University of Edinburgh（爱丁堡大学）
Recent advances in deep generative models have led to impressive results in a variety of application domains. Motivated by the possibility that deep learning models might memorize part of the input data, there have been increased efforts to understand how memorization arises. In this work, we extend a recently proposed measure of memorization for supervised learning (Feldman, 2019) to the unsupervised density estimation problem and adapt it to be more computationally efficient. Next, we present a study that demonstrates how memorization can occur in probabilistic deep generative models such as…
Tackling Noisy Labels with Network Parameter Additive Decomposition
National University of Defense Technology（国防科技大学）；University of Sydney（悉尼大学）；Beihang University（北京航空航天大学）；University of Science and Technology of China（中国科学技术大学）；Hong Kong Baptist University（香港浸会大学）
Applied AI Institute, Deakin University（迪肯大学应用人工智能研究所）
Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not effectively leverage the short-term memory held in the controller. We hypothesize that this scheme of writing is suboptimal in memory utilization and introduces redundant computation. To validate our hypothesis, we derive a theoretical bound on the amount of information stored in a RAM-like system and formulate an optimization problem that maximizes the bound. …
We propose an approach to address two issues that commonly occur during training of unsupervised GANs. First, since GANs use only a continuous latent distribution to embed multiple classes or clusters of data, they often do not correctly handle the structural discontinuity between disparate classes in a latent space. Second, discriminators of GANs easily forget about past generated samples by generators, incurring instability during adversarial training. We argue that these two infamous problems of unsupervised GAN training can be largely alleviated by a learnable memory network to which both …
Beihang University（北京航空航天大学）；The University of Tokyo（东京大学）；RIKEN Center for AIP（理化学研究所人工智能研究中心）
People usually believe that network pruning not only reduces the computational cost of deep networks, but also prevents overfitting by decreasing model capacity. However, our work surprisingly discovers that network pruning sometimes even aggravates overfitting. We report an unexpected sparse double descent phenomenon that, as we increase model sparsity via network pruning, test performance first gets worse (due to overfitting), then gets better (due to relieved overfitting), and gets worse at last (due to forgetting useful information). While recent studies focused on the deep double descent …
Mitigating Memorization of Noisy Labels by Clipping the Model Prediction
Southern University of Science and Technology（南方科技大学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；South China University of Technology（华南理工大学）；Nanyang Technological University（南洋理工大学）；RIKEN AIP（理化学研究所人工智能研究中心）
Lifelong learning with deep neural networks is well-known to suffer from catastrophic forgetting: the performance on previous tasks drastically degrades when learning a new task. To alleviate this effect, we propose to leverage a large stream of unlabeled data easily obtainable in the wild. In particular, we design a novel class-incremental learning scheme with (a) a new distillation loss, termed global distillation, (b) a learning strategy to avoid overfitting to the most recent task, and (c) a confidence-based sampling method to effectively leverage unlabeled external data. Our experimental …
Google（谷歌）；University of California, Berkeley（加州大学伯克利分校）
The focus of this paper is on intrinsic methods to detect overfitting. By intrinsic methods, we mean methods that rely only on the model and the training data, as opposed to traditional methods (we call them extrinsic methods) that rely on performance on a test set or on bounds from model complexity. We propose a family of intrinsic methods, called Counterfactual Simulation (CFS), which analyze the flow of training examples through the model by identifying and perturbing rare patterns. By applying CFS to logic circuits we get a method that has no hyper-parameters and works uniformly across dif…
This paper studies the relationship between the classification performed by deep neural networks (DNNs) and the decision of various classical classifiers, namely k-nearest neighbours (k-NN), support vector machines (SVM) and logistic regression (LR), at various layers of the network. This comparison provides us with new insights as to the ability of neural networks to both memorize the training data and generalize to new data at the same time, where k-NN serves as the ideal estimator that perfectly memorizes the data. We show that memorization of non-generalizing networks happens only at the l…
Korea Advanced Institute of Science and Technology（韩国高等科学技术院）
Since deep neural networks are over-parameterized, they can memorize noisy examples. We address such a memorization issue in the presence of label noise. From the fact that deep neural networks cannot generalize to neighborhoods of memorized features, we hypothesize that noisy examples do not consistently incur small losses on the network under a certain perturbation. Based on this, we propose a novel training method called Learning with Ensemble Consensus (LEC) that prevents overfitting to noisy examples by removing them based on the consensus of an ensemble of perturbed networks. One of the …
Nowadays, machine learning models, especially neural networks, become prevalent in many real-world applications.These models are trained based on a one-way trip from user data: as long as users contribute their data, there is no way to withdraw; and it is well-known that a neural network memorizes its training data. This contradicts the "right to be forgotten" clause of GDPR, potentially leading to law violations. To this end, machine unlearning becomes a popular research topic, which allows users to eliminate memorization of their private data from a trained machine learning model.In this pap…
Catastrophic Forgetting Mitigation via Discrepancy-Weighted Experience Replay
Institute of Software Chinese Academy of Science, Beijing, China（中国科学院软件研究所）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学）；Advanced Institute of Big Data, Beijing, China（大数据先进研究院）
Corti, Denmark（丹麦Corti公司）；University of Copenhagen, Department of Computer Science, Denmark（丹麦哥本哈根大学计算机科学系）；Biomediq A/S, Denmark（丹麦Biomediq公司）
Despite all the success that deep neural networks have seen in classifying certain datasets, the challenge of finding optimal solutions that generalize still remains. In this paper, we propose the Boundary Optimizing Network (BON), a new approach to generalization for deep neural networks when used for supervised learning. Given a classification network, we propose to use a collaborative generative network that produces new synthetic data points in the form of perturbations of original data points. In this way, we create a data support around each original data point which prevents decision bo…
