Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDeep Learning on a Data Diet: Finding Important Examples Early in Training
68
0
0.0
(
0
)
Added by
Gintare Karolina Dziugaite
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
The recent success of deep learning has partially been driven by training increasingly overparametrized networks on ever larger datasets. It is therefore natural to ask: how much of the data is superfluous, which examples are important for generalization, and how do we find them? In this work, we make the striking observation that, on standard vision benchmarks, the initial loss gradient norm of individual training examples, averaged over several weight initializations, can be used to identify a smaller set of training data that is important for generalization. Furthermore, after only a few epochs of training, the information in gradient norms is reflected in the normed error--L2 distance between the predicted probabilities and one hot labels--which can be used to prune a significant fraction of the dataset without sacrificing test accuracy. Based on this, we propose data pruning methods which use only local information early in training, and connect them to recent work that prunes data by discarding examples that are rarely forgotten over the course of training. Our methods also shed light on how the underlying data distribution shapes the training dynamics: they rank examples based on their importance for generalization, detect noisy examples and identify subspaces of the models data representation that are relatively stable over training.
rate research
Read More
Deep neural networks have been shown to be very powerful modeling tools for many supervised learning tasks involving complex input patterns. However, they can also easily overfit to training set biases and label noises. In addition to various regularizers, example reweighting algorithms are popular solutions to these problems, but they require careful tuning of additional hyperparameters, such as example mining schedules and regularization hyperparameters. In contrast to past reweighting methods, which typically consist of functions of the cost value of each example, in this work we propose a novel meta-learning algorithm that learns to assign weights to training examples based on their gradient directions. To determine the example weights, our method performs a meta gradient descent step on the current mini-batch example weights (which are initialized from zero) to minimize the loss on a clean unbiased validation set. Our proposed method can be easily implemented on any type of deep network, does not require any additional hyperparameter tuning, and achieves impressive performance on class imbalance and corrupted label problems where only a small amount of clean validation data is available.
Graph deep learning models, such as graph convolutional networks (GCN) achieve remarkable performance for tasks on graph data. Similar to other types of deep models, graph deep learning models often suffer from adversarial attacks. However, compared with non-graph data, the discrete features, graph connections and different definitions of imperceptible perturbations bring unique challenges and opportunities for the adversarial attacks and defenses for graph data. In this paper, we propose both attack and defense techniques. For attack, we show that the discreteness problem could easily be resolved by introducing integrated gradients which could accurately reflect the effect of perturbing certain features or edges while still benefiting from the parallel computations. For defense, we observe that the adversarially manipulated graph for the targeted attack differs from normal graphs statistically. Based on this observation, we propose a defense approach which inspects the graph and recovers the potential adversarial perturbations. Our experiments on a number of datasets show the effectiveness of the proposed methods.
Finding valuable training data points for deep neural networks has been a core research challenge with many applications. In recent years, various techniques for calculating the value of individual training datapoints have been proposed for explaining trained models. However, the value of a training datapoint also depends on other selected training datapoints - a notion that is not explicitly captured by existing methods. In this paper, we study the problem of selecting high-value subsets of training data. The key idea is to design a learnable framework for online subset selection, which can be learned using mini-batches of training data, thus making our method scalable. This results in a parameterized convex subset selection problem that is amenable to a differentiable convex programming paradigm, thus allowing us to learn the parameters of the selection model in end-to-end training. Using this framework, we design an online alternating minimization-based algorithm for jointly learning the parameters of the selection model and ML model. Extensive evaluation on a synthetic dataset, and three standard datasets, show that our algorithm finds consistently higher value subsets of training data, compared to the recent state-of-the-art methods, sometimes ~20% higher value than existing methods. The subsets are also useful in finding mislabelled training data. Our algorithm takes running time comparable to the existing valuation functions.
Exploration of new superconductors still relies on the experience and intuition of experts and is largely a process of experimental trial and error. In one study, only 3% of the candidate materials showed superconductivity. Here, we report the first deep learning model for finding new superconductors. We introduced the method named reading periodic table which represented the periodic table in a way that allows deep learning to learn to read the periodic table and to learn the law of elements for the purpose of discovering novel superconductors that are outside the training data. It is recognized that it is difficult for deep learning to predict something outside the training data. Although we used only the chemical composition of materials as information, we obtained an $R^{2}$ value of 0.92 for predicting $T_text{c}$ for materials in a database of superconductors. We also introduced the method named garbage-in to create synthetic data of non-superconductors that do not exist. Non-superconductors are not reported, but the data must be required for deep learning to distinguish between superconductors and non-superconductors. We obtained three remarkable results. The deep learning can predict superconductivity for a material with a precision of 62%, which shows the usefulness of the model; it found the recently discovered superconductor CaBi2 and another one Hf0.5Nb0.2V2Zr0.3, neither of which is in the superconductor database; and it found Fe-based high-temperature superconductors (discovered in 2008) from the training data before 2008. These results open the way for the discovery of new high-temperature superconductor families. The candidate materials list, data, and method are openly available from the link https://github.com/tomo835g/Deep-Learning-to-find-Superconductors.
This paper presents the first comprehensive empirical study demonstrating the efficacy of the Brain Floating Point (BFLOAT16) half-precision format for Deep Learning training across image classification, speech recognition, language modeling, generative networks and industrial recommendation systems. BFLOAT16 is attractive for Deep Learning training for two reasons: the range of values it can represent is the same as that of IEEE 754 floating-point format (FP32) and conversion to/from FP32 is simple. Maintaining the same range as FP32 is important to ensure that no hyper-parameter tuning is required for convergence; e.g., IEEE 754 compliant half-precision floating point (FP16) requires hyper-parameter tuning. In this paper, we discuss the flow of tensors and various key operations in mixed precision training, and delve into details of operations, such as the rounding modes for converting FP32 tensors to BFLOAT16. We have implemented a method to emulate BFLOAT16 operations in Tensorflow, Caffe2, IntelCaffe, and Neon for our experiments. Our results show that deep learning training using BFLOAT16 tensors achieves the same state-of-the-art (SOTA) results across domains as FP32 tensors in the same number of iterations and with no changes to hyper-parameters.
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
