skip to main content


Title: Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates
Learning with noisy labels is a common challenge in supervised learning. Existing approaches often require practitioners to specify noise rates, i.e., a set of parameters controlling the severity of label noises in the problem, and the specifications are either assumed to be given or estimated using additional steps. In this work, we introduce a new family of loss functions that we name as peer loss functions, which enables learning from noisy labels and does not require a priori specification of the noise rates. Peer loss functions work within the standard empirical risk minimization (ERM) framework. We show that, under mild conditions, performing ERM with peer loss functions on the noisy data leads to the optimal or a near-optimal classifier as if performing ERM over the clean training data, which we do not have access to. We pair our results with an extensive set of experiments. Peer loss provides a way to simplify model development when facing potentially noisy training labels, and can be promoted as a robust candidate loss function in such situations.  more » « less
Award ID(s):
2007951
NSF-PAR ID:
10290970
Author(s) / Creator(s):
;
Editor(s):
Daumé III, Hal; Singh, Aarti
Date Published:
Journal Name:
Proceedings of the 37th International Conference on Machine Learning
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    The presence of label noise often misleads the training of deep neural networks. Departing from the recent literature which largely assumes the label noise rate is only determined by the true label class, the errors in human-annotated labels are more likely to be dependent on the difficulty levels of tasks, resulting in settings with instance-dependent label noise. We first provide evidences that the heterogeneous instance-dependent label noise is effectively down-weighting the examples with higher noise rates in a non-uniform way and thus causes imbalances, rendering the strategy of directly applying methods for class-dependent label noise questionable. Built on a recent work peer loss [24], we then propose and study the potentials of a second-order approach that leverages the estimation of several covariance terms defined between the instance-dependent noise rates and the Bayes optimal label. We show that this set of second-order statistics successfully captures the induced imbalances. We further proceed to show that with the help of the estimated second-order statistics, we identify a new loss function whose expected risk of a classifier under instance-dependent label noise is equivalent to a new problem with only class-dependent label noise. This fact allows us to apply existing solutions to handle this better-studied setting. We provide an efficient procedure to estimate these second-order statistics without accessing either ground truth labels or prior knowledge of the noise rates. Experiments on CIFAR10 and CIFAR100 with synthetic instance-dependent label noise and Clothing1M with real-world human label noise verify our approach. Our implementation is available at https://github.com/UCSC-REAL/CAL. 
    more » « less
  2. Obeid, I. ; Selesnik, I. ; Picone, J. (Ed.)
    The Neuronix high-performance computing cluster allows us to conduct extensive machine learning experiments on big data [1]. This heterogeneous cluster uses innovative scheduling technology, Slurm [2], that manages a network of CPUs and graphics processing units (GPUs). The GPU farm consists of a variety of processors ranging from low-end consumer grade devices such as the Nvidia GTX 970 to higher-end devices such as the GeForce RTX 2080. These GPUs are essential to our research since they allow extremely compute-intensive deep learning tasks to be executed on massive data resources such as the TUH EEG Corpus [2]. We use TensorFlow [3] as the core machine learning library for our deep learning systems, and routinely employ multiple GPUs to accelerate the training process. Reproducible results are essential to machine learning research. Reproducibility in this context means the ability to replicate an existing experiment – performance metrics such as error rates should be identical and floating-point calculations should match closely. Three examples of ways we typically expect an experiment to be replicable are: (1) The same job run on the same processor should produce the same results each time it is run. (2) A job run on a CPU and GPU should produce identical results. (3) A job should produce comparable results if the data is presented in a different order. System optimization requires an ability to directly compare error rates for algorithms evaluated under comparable operating conditions. However, it is a difficult task to exactly reproduce the results for large, complex deep learning systems that often require more than a trillion calculations per experiment [5]. This is a fairly well-known issue and one we will explore in this poster. Researchers must be able to replicate results on a specific data set to establish the integrity of an implementation. They can then use that implementation as a baseline for comparison purposes. A lack of reproducibility makes it very difficult to debug algorithms and validate changes to the system. Equally important, since many results in deep learning research are dependent on the order in which the system is exposed to the data, the specific processors used, and even the order in which those processors are accessed, it becomes a challenging problem to compare two algorithms since each system must be individually optimized for a specific data set or processor. This is extremely time-consuming for algorithm research in which a single run often taxes a computing environment to its limits. Well-known techniques such as cross-validation [5,6] can be used to mitigate these effects, but this is also computationally expensive. These issues are further compounded by the fact that most deep learning algorithms are susceptible to the way computational noise propagates through the system. GPUs are particularly notorious for this because, in a clustered environment, it becomes more difficult to control which processors are used at various points in time. Another equally frustrating issue is that upgrades to the deep learning package, such as the transition from TensorFlow v1.9 to v1.13, can also result in large fluctuations in error rates when re-running the same experiment. Since TensorFlow is constantly updating functions to support GPU use, maintaining an historical archive of experimental results that can be used to calibrate algorithm research is quite a challenge. This makes it very difficult to optimize the system or select the best configurations. The overall impact of all of these issues described above is significant as error rates can fluctuate by as much as 25% due to these types of computational issues. Cross-validation is one technique used to mitigate this, but that is expensive since you need to do multiple runs over the data, which further taxes a computing infrastructure already running at max capacity. GPUs are preferred when training a large network since these systems train at least two orders of magnitude faster than CPUs [7]. Large-scale experiments are simply not feasible without using GPUs. However, there is a tradeoff to gain this performance. Since all our GPUs use the NVIDIA CUDA® Deep Neural Network library (cuDNN) [8], a GPU-accelerated library of primitives for deep neural networks, it adds an element of randomness into the experiment. When a GPU is used to train a network in TensorFlow, it automatically searches for a cuDNN implementation. NVIDIA’s cuDNN implementation provides algorithms that increase the performance and help the model train quicker, but they are non-deterministic algorithms [9,10]. Since our networks have many complex layers, there is no easy way to avoid this randomness. Instead of comparing each epoch, we compare the average performance of the experiment because it gives us a hint of how our model is performing per experiment, and if the changes we make are efficient. In this poster, we will discuss a variety of issues related to reproducibility and introduce ways we mitigate these effects. For example, TensorFlow uses a random number generator (RNG) which is not seeded by default. TensorFlow determines the initialization point and how certain functions execute using the RNG. The solution for this is seeding all the necessary components before training the model. This forces TensorFlow to use the same initialization point and sets how certain layers work (e.g., dropout layers). However, seeding all the RNGs will not guarantee a controlled experiment. Other variables can affect the outcome of the experiment such as training using GPUs, allowing multi-threading on CPUs, using certain layers, etc. To mitigate our problems with reproducibility, we first make sure that the data is processed in the same order during training. Therefore, we save the data from the last experiment and to make sure the newer experiment follows the same order. If we allow the data to be shuffled, it can affect the performance due to how the model was exposed to the data. We also specify the float data type to be 32-bit since Python defaults to 64-bit. We try to avoid using 64-bit precision because the numbers produced by a GPU can vary significantly depending on the GPU architecture [11-13]. Controlling precision somewhat reduces differences due to computational noise even though technically it increases the amount of computational noise. We are currently developing more advanced techniques for preserving the efficiency of our training process while also maintaining the ability to reproduce models. In our poster presentation we will demonstrate these issues using some novel visualization tools, present several examples of the extent to which these issues influence research results on electroencephalography (EEG) and digital pathology experiments and introduce new ways to manage such computational issues. 
    more » « less
  3. null (Ed.)
    Human-annotated labels are often prone to noise, and the presence of such noise will degrade the performance of the resulting deep neural network (DNN) models. Much of the literature (with several recent exceptions) of learning with noisy labels focuses on the case when the label noise is independent of features. Practically, annotations errors tend to be instance-dependent and often depend on the difficulty levels of recognizing a certain task. Applying existing results from instance-independent settings would require a significant amount of estimation of noise rates. Therefore, providing theoretically rigorous solutions for learning with instance-dependent label noise remains a challenge. In this paper, we propose CORES (COnfidence REgularized Sample Sieve), which progressively sieves out corrupted examples. The implementation of CORES does not require specifying noise rates and yet we are able to provide theoretical guarantees of CORES in filtering out the corrupted examples. This high-quality sample sieve allows us to treat clean examples and the corrupted ones separately in training a DNN solution, and such a separation is shown to be advantageous in the instance-dependent noise setting. We demonstrate the performance of CORES^2 on CIFAR10 and CIFAR100 datasets with synthetic instance-dependent label noise and Clothing1M with real-world human noise. As of independent interests, our sample sieve provides a generic machinery for anatomizing noisy datasets and provides a flexible interface for various robust training techniques to further improve the performance. Code is available at https://github.com/UCSC-REAL/cores. 
    more » « less
  4. Producing high-quality labeled data is a challenge in any supervised learning problem, where in many cases, human involvement is necessary to ensure the label quality. However, human annotations are not flawless, especially in the case of a challenging problem. In nontrivial problems, the high disagreement among annotators results in noisy labels, which affect the performance of any machine learning model. In this work, we consider three noise reduction strategies to improve the label quality in the Article-Comment Alignment Problem, where the main task is to classify article-comment pairs according to their relevancy level. The first considered labeling disagreement reduction strategy utilizes annotators' background knowledge during the label aggregation step. The second strategy utilizes user disagreement during the training process. In the third and final strategy, we ask annotators to perform corrections and relabel the examples with noisy labels. We deploy these strategies and compare them to a resampling strategy for addressing the class imbalance, another common supervised learning challenge. These alternatives were evaluated on ACAP, a multiclass text pairs classification problem with highly imbalanced data, where one of the classes represents at most 15% of the dataset's entire population. Our results provide evidence that considered strategies can reduce disagreement between annotators. However, data quality improvement is insufficient to enhance classification accuracy in the article-comment alignment problem, which exhibits a high-class imbalance. The model performance is enhanced for the same problem by addressing the imbalance issue with a weight loss-based class distribution resampling. We show that allowing the model to pay more attention to the minority class during the training process with the presence of noisy examples improves the test accuracy by 3%. 
    more » « less
  5. Existing research on learning with noisy labels mainly focuses on synthetic label noise. Synthetic label noise, though has clean structures which greatly enable statistical analyses, often fails to model the real-world noise patterns. The recent literature has observed several efforts to offer real-world noisy datasets, e.g., Food-101N, WebVision, and Clothing1M. Yet the existing efforts suffer from two caveats: firstly, the lack of ground-truth verification makes it hard to theoretically study the property and treatment of real-world label noise. Secondly, these efforts are often of large scales, which may result in unfair comparisons of robust methods within reasonable and accessible computation power. To better understand real-world label noise, it is important to establish controllable and moderate-sized real-world noisy datasets with both ground-truth and noisy labels. This work presents two new benchmark datasets, which we name as CIFAR-10N, CIFAR-100N, equipping the training datasets of CIFAR-10 and CIFAR-100 with human-annotated real-world noisy labels that we collect from Amazon Mechanical Turk. We quantitatively and qualitatively show that real-world noisy labels follow an instance-dependent pattern rather than the classically assumed and adopted ones (e.g., class-dependent label noise). We then initiate an effort to benchmark a subset of the existing solutions using CIFAR-10N and CIFAR-100N. We further proceed to study the memorization of correct and wrong predictions, which further illustrates the difference between human noise and class-dependent synthetic noise. We show indeed the real-world noise patterns impose new and outstanding challenges as compared to synthetic label noise. These observations require us to rethink the treatment of noisy labels, and we hope the availability of these two datasets would facilitate the development and evaluation of future learning with noisy label solutions. The corresponding datasets and the leaderboard are publicly available at http://noisylabels.com. 
    more » « less