arXiv research

Unsupervised learning models can produce accurate but misleading predictions.

Recently, multilayer bootstrap network (MBN) has demonstrated promising performance in unsupervised dimensionality reduction. It can learn compact representations in standard data sets, i.e. MNIST and RCV1. However, as a bootstrap method, the prediction complexity of MBN is high. In this paper, we propose an unsupervis…

Unsupervised machine translation---i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora---seems impossible, but nevertheless, Lample et al. (2018) recently proposed a fully unsupervised machine translation (MT) model. The model relies heavily on an adversari…

This research shows unsupervised GANs can perform object segmentation without labels.

This paper addresses the problem of unsupervised clustering which remains one of the most fundamental challenges in machine learning and artificial intelligence. We propose the clustered generator model for clustering which contains both continuous and discrete latent variables. Discrete latent variables model the clus…

The authors advocate for more rigorous unsupervised cross-lingual learning methods.

A new method generates meta-tasks using generative models for unsupervised learning.

New model combines ICA and HMM for unsupervised learning of nonstationary time series.

This paper proves the theoretical advantage of unsupervised pretraining for machine learning tasks.

This paper develops a federated EM algorithm for unsupervised learning of mixture models.

Unsupervised pre-training improves model generalization, but lacks theoretical understanding.

In this paper we take a problem of unsupervised nodes clustering on graphs and show how recent advances in attention models can be applied successfully in a "hard" regime of the problem. We propose an unsupervised algorithm that encodes Bethe Hessian embeddings by optimizing soft modularity loss and argue that our mode…

Paper proposes a novel unsupervised feature selection method using K-means and ADMM.

Diffusion models enhance speech without supervision.

Disentangled representations have recently been shown to improve fairness, data efficiency and generalisation in simple supervised and reinforcement learning tasks. To extend the benefits of disentangled representations to more complex domains and practical applications, it is important to enable hyperparameter tuning …

Paper presents a workflow for reliable unsupervised learning in science.

New method shows supervised learning can mimic unsupervised learning effectively.

Generating versatile and appropriate synthetic speech requires control over the output expression separate from the spoken text. Important non-textual speech variation is seldom annotated, in which case output control must be learned in an unsupervised fashion. In this paper, we perform an in-depth study of methods for…

Unsupervised model detects healthcare fraud from patient visit data.

CoDAG combines domain adaptation and generalization for unsupervised continual domain shift learning.

Improved disentanglement of data factors using recursive training.

Unsupervised classification methods learn a discriminative classifier from unlabeled data, which has been proven to be an effective way of simultaneously clustering the data and training a classifier from the data. Various unsupervised classification methods obtain appealing results by the classifiers learned in an uns…

Self-supervised model detects phoneme boundaries without annotations.

Proposes manifold-based unsupervised anomaly detection for visual data.

Improves model calibration and selection in unsupervised domain adaptation.

Outlier detection is a key field of machine learning for identifying abnormal data objects. Due to the high expense of acquiring ground truth, unsupervised models are often chosen in practice. To compensate for the unstable nature of unsupervised algorithms, practitioners from high-stakes fields like finance, health, a…

Score calibration enables automatic speaker recognizers to make cost-effective accept / reject decisions. Traditional calibration requires supervised data, which is an expensive resource. We propose a 2-component GMM for unsupervised calibration and demonstrate good performance relative to a supervised baseline on NIST…

In this work, we investigate unsupervised representation learning on medical time series, which bears the promise of leveraging copious amounts of existing unlabeled data in order to eventually assist clinical decision making. By evaluating on the prediction of clinically relevant outcomes, we show that in a practical …

Tensor networks improve unsupervised learning performance.

A novel algorithm for unsupervised graph representation learning combining coarsening and mutual information maximization.

Using supervised machine learning approaches to recognize human activities from on-body wearable accelerometers generally requires a large amount of labelled data. When ground truth information is not available, too expensive, time consuming or difficult to collect, one has to rely on unsupervised approaches. This pape…

Unsupervised learning models can be indistinguishable without identifiability, leading to unreliable representations.

SKADA-bench evaluates unsupervised DA methods across diverse modalities.

Unsupervised ranking faces one critical challenge in evaluation applications, that is, no ground truth is available. When PageRank and its variants show a good solution in related subjects, they are applicable only for ranking from link-structure data. In this work, we focus on unsupervised ranking from multi-attribute…

Kauri is a novel unsupervised binary tree for clustering that outperforms existing methods.

A new deep learning framework selects representative samples for unsupervised learning.

A new method selects features for clustering using a block model.

We study a variant of the variational autoencoder model (VAE) with a Gaussian mixture as a prior distribution, with the goal of performing unsupervised clustering through deep generative models. We observe that the known problem of over-regularisation that has been shown to arise in regular VAEs also manifests itself i…

Unsupervised clustering of series using dynamic programming.

Super-AND improves unsupervised embedding learning with 89.2% accuracy on CIFAR-10.

Study shows double and triple descent in unsupervised autoencoders, improving performance in various tasks.

TGLS generates text by optimizing search results and learning from them.

Study subjective perception of low light restored images and develop an unsupervised QA model.

A major goal of unsupervised learning is to discover data representations that are useful for subsequent tasks, without access to supervised labels during training. Typically, this involves minimizing a surrogate objective, such as the negative log likelihood of a generative model, with the hope that representations us…

Ensemble unsupervised anomaly detection using IRT for hidden ground truth.

The task of matching co-referent records is known among other names as rocord linkage. For large record-linkage problems, often there is little or no labeled data available, but unlabeled data shows a reasonable clear structure. For such problems, unsupervised or semi-supervised methods are preferable to supervised met…

For better classification generative models are used to initialize the model and model features before training a classifier. Typically it is needed to solve separate unsupervised and supervised learning problems. Generative restricted Boltzmann machines and deep belief networks are widely used for unsupervised learnin…

LCBM model improves image classification without human supervision.