A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Paper tackles instance-dependent label noise by approximating it with part-dependent noise.
A method to approximate instance-dependent label noise using instance-confidence embedding.
In learning with noisy labels, for every instance, its label can randomly walk to other classes following a transition distribution which is named a noise model. Well-studied noise models are all instance-independent, namely, the transition depends only on the original label but not the instance itself, and thus they a…
BeGIN benchmarks GNNs for instance-dependent label noise in graphs.
Paper proposes a universal probabilistic model for handling instance-dependent label noise.
A new method handles label noise by leveraging causal information.
CORES2 removes noisy labels by sieving out corrupted examples.
The paper analyzes how deep neural networks handle noisy labels and finds disparate impacts.
This paper identifies and estimates the label noise transition matrix without ground truth labels.
New method for certified unlearning reduces noise injection.
Method reweights instances and classes to improve robustness in noisy data.
New research shows that binary classification can be done with noisy data, but only if there are clean samples available.
It is widely known in the machine learning community that class noise can be (and often is) detrimental to inducing a model of the data. Many current approaches use a single, often biased, measurement to determine if an instance is noisy. A biased measure may work well on certain data sets, but it can also be less effe…
The presence of noisy instances in mobile phone data is a fundamental issue for classifying user phone call behavior (i.e., accept, reject, missed and outgoing), with many potential negative consequences. The classification accuracy may decrease and the complexity of the classifiers may increase due to the number of re…
Batch Normalization (BN)(Ioffe and Szegedy 2015) normalizes the features of an input image via statistics of a batch of images and hence BN will bring the noise to the gradient of the training loss. Previous works indicate that the noise is important for the optimization and generalization of deep neural networks, but …
Vote-boosting is a sequential ensemble learning method in which the individual classifiers are built on different weighted versions of the training data. To build a new classifier, the weight of each training instance is determined in terms of the degree of disagreement among the current ensemble predictions for that i…
MARVEL curbs memorization of noisy labels in deep nets.
New LP method recovers MAP solution from noisy stable instances.
Study improves model robustness in noisy datasets.
In this paper, we consider a novel machine learning problem, that is, learning a classifier from noisy label distributions. In this problem, each instance with a feature vector belongs to at least one group. Then, instead of the true label of each instance, we observe the label distribution of the instances associated …
Inserting label noise can improve model accuracy and fairness.
Instance- and Label-dependent label Noise (ILN) widely exists in real-world datasets but has been rarely studied. In this paper, we focus on Bounded Instance- and Label-dependent label Noise (BILN), a particular case of ILN where the label noise rates -- the probabilities that the true labels of examples flip into the …
NoiseRank reduces label noise without supervision, improving classification accuracy.
DynaCor detects noisy labels by learning from corrupted training signals.
In Machine Learning, ensemble methods have been receiving a great deal of attention. Techniques such as Bagging and Boosting have been successfully applied to a variety of problems. Nevertheless, such techniques are still susceptible to the effects of noise and outliers in the training data. We propose a new method for…
In this paper, we consider batch supervised learning where an adversary is allowed to corrupt instances with arbitrarily large noise. The adversary is allowed to corrupt any features in each instance and the adversary can change their values in any way. This noise is introduced on test instances and the algorithm r…
Diffusion-GAN uses diffusion to improve GAN training stability and realism.
The objective function of a matrix factorization model usually aims to minimize the average of a regression error contributed by each element. However, given the existence of stochastic noises, the implicit deviations of sample data from their true values are almost surely diverse, which makes each data point not equal…
Proposes a new model for noisy labels considering multiple labelers and adversarial attacks.
A similarity label indicates whether two instances belong to the same class while a class label shows the class of the instance. Without class labels, a multi-class classifier could be learned from similarity-labeled pairwise data by meta classification learning. However, since the similarity label is less informative …
New method uses SLL to create masks for PX in noisy optimization problems.
Proposes MGPLL for PL learning with non-random noise.
Not all instances in a data set are equally beneficial for inducing a model of the data. Some instances (such as outliers or noise) can be detrimental. However, at least initially, the instances in a data set are generally considered equally in machine learning algorithms. Many current approaches for handling noisy and…
Traditionally, the random noise is equally injected when training with different data instances in the field of differential privacy (DP). In this paper, we first give sharper excess risk bounds of DP stochastic gradient descent (SGD) method. Considering most of the previous methods are under convex conditions, we use …
Study bounds noise level in linear regression with dependent data.
Federated learning performs distributed model training using local data hosted by agents. It shares only model parameter updates for iterative aggregation at the server. Although it is privacy-preserving by design, federated learning is vulnerable to noise corruption of local agents, as demonstrated in the previous stu…
Study efficient learning of halfspaces with constant noise tolerance.
Supervised deep-embedding methods project inputs of a domain to a representational space in which same-class instances lie near one another and different-class instances lie far apart. We propose a probabilistic method that treats embeddings as random variables. Extending a state-of-the-art deterministic method, Protot…
Noise-ignorant empirical risk minimization achieves state-of-the-art performance on noisy data.
Study on noise models for noisy labels in NLP.
The paper proposes a method to detect and filter noisy or mislabeled data using pointwise mutual information.
RECLAIM discovers causal graphs in cyclic, noisy systems.
A key requirement for supervised machine learning is labeled training data, which is created by annotating unlabeled data with the appropriate class. Because this process can in many cases not be done by machines, labeling needs to be performed by human domain experts. This process tends to be expensive both in time an…
Existing relation classification methods that rely on distant supervision assume that a bag of sentences mentioning an entity pair are all describing a relation for the entity pair. Such methods, performing classification at the bag level, cannot identify the mapping between a relation and a sentence, and largely suffe…
This paper proposes an active metric learning method for clustering with pairwise constraints.
Paper improves image classification accuracy with a new Noise Modeling Network.
Collecting large-scale data with clean labels for supervised training of neural networks is practically challenging. Although noisy labels are usually cheap to acquire, existing methods suffer a lot from label noise. This paper targets at the challenge of robust training at high label noise regimes. The key insight to …
Removing or filtering outliers and mislabeled instances prior to training a learning algorithm has been shown to increase classification accuracy. A popular approach for handling outliers and mislabeled instances is to remove any instance that is misclassified by a learning algorithm. However, an examination of which l…