arXiv research

Paper tackles noisy labels by compressing feature representations.

A new method compresses conditional distributions of labelled data.

The paper proposes a bio-inspired framework for better compression and adversarial robustness in machine learning models.

In this paper, we investigate the degree to which the encoding of a $β$-VAE captures label information across multiple architectures on Binary Static MNIST and Omniglot. Even though they are trained in a completely unsupervised manner, we demonstrate that a $β$-VAE can retain a large amount of label information, even w…

Learnable multiclass hypothesis classes don't always have a sample compression scheme of fixed size.

We introduce a new and improved characterization of the label complexity of disagreement-based active learning, in which the leading quantity is the version space compression set size. This quantity is defined as the size of the smallest subset of the training data that induces the same version space. We show various a…

Improves compression of neural networks for embedded systems.

Investigates principles of generalization in list learning, refutes sample compression conjecture.

Electron Cryo-Tomography (ECT) enables 3D visualization of macromolecule structure inside single cells. Macromolecule classification approaches based on convolutional neural networks (CNN) were developed to separate millions of macromolecules captured from ECT systematically. However, given the fast accumulation of ECT…

Neural networks compress uninformative input directions, improving test error.

A CAE improves DNN's outlier and adversary defense.

Paper proposes efficient GCN learning method for limited data.

A new framework CL embeds features and labels for multi-label classification.

Paper detects common subtrees with identical labels in trees.

Profile entropy measures learnability and compressibility of discrete distributions.

Deep neural network compression techniques such as pruning and weight tensor decomposition usually require fine-tuning to recover the prediction accuracy when the compression ratio is high. However, conventional fine-tuning suffers from the requirement of a large training set and the time-consuming training procedure. …

Given labeled points in a high-dimensional vector space, we seek a low-dimensional subspace such that projecting onto this subspace maintains some prescribed distance between points of differing labels. Intended applications include compressive classification. Taking inspiration from large margin nearest neighbor class…

Reduces multiclass and regression compression schemes to binary ones.

Study reduces memory needs for active learning with enriched queries.

Representing patterns as labeled graphs is becoming increasingly common in the broad field of computational intelligence. Accordingly, a wide repertoire of pattern recognition tools, such as classifiers and knowledge discovery procedures, are nowadays available and tested for various datasets of labeled graphs. However…

New methods identify local clusters in graphs with few labels.

This work compresses BERT into simple neural networks using unlabeled data.

Soft labeling impacts OOD detection in neural networks.

This work automates CNN model compression for mobile devices.

How to obtain a model with good interpretability and performance has always been an important research topic. In this paper, we propose rectified decision trees (ReDT), a knowledge distillation based decision trees rectification with high interpretability, small model size, and empirical soundness. Specifically, we ext…

Many modern applications deal with multi-label data, such as functional categorizations of genes, image labeling and text categorization. Classification of such data with a large number of labels and latent dependencies among them is a challenging task, and it becomes even more challenging when the data is received onl…

Efficient algorithms recover two sparse models from a mix of linear queries.

Source coding is the canonical problem of data compression in information theory. In a locally encodable source coding, each compressed bit depends on only few bits of the input. In this paper, we show that a recently popular model of semi-supervised clustering is equivalent to locally encodable source coding. In this …

Maximizing margins leads to lossless compression of training data.

Paper establishes generalization bounds for representation learning using Minimum Description Length.

Adjoined Networks trains both base and compressed networks together for efficient model compression.

Clustering, like covariate selection for classification, is an important step to compress and interpret the data. However, clustering of covariates is often performed independently of the classification step, which can lead to undesirable clustering results that harm interpretability and compression rate. Therefore, we…

Compressed Federated Distillation reduces communication in federated learning.

Compressing giant neural networks has gained much attention for their extensive applications on edge devices such as cellphones. During the compressing process, one of the most important procedures is to retrain the pre-trained models using the original training dataset. However, due to the consideration of security, p…

Paper proposes a new method for training small models on regression problems.

Convolutional neural networks (CNNs) achieve state-of-the-art performance in a wide variety of tasks in computer vision. However, interpreting CNNs still remains a challenge. This is mainly due to the large number of parameters in these networks. Here, we investigate the role of compression and particularly pruning fil…

Study explores various KD methods to improve model performance.

This paper evaluates conformal prediction for aerial image classification in challenging environments.

Unified method learns latent spaces from labeled data.

In this paper we propose a measure of clustering quality or accuracy that is appropriate in situations where it is desirable to evaluate a clustering algorithm by somehow comparing the clusters it produces with ``ground truth' consisting of classes assigned to the patterns by manual means or some other means in whose v…

New algorithm learns mappings between metric spaces, achieving strong consistency.

In the era of big data, learning from categorical features with very large vocabularies (e.g., 28 million for the Criteo click prediction dataset) has become a practical challenge for machine learning researchers and practitioners. We design a highly-scalable vocabulary compression algorithm that seeks to maximize the …

UVeQFed tackles FL model compression over limited channels.

This work proposes a novel method for semi-supervised learning from partially labeled massive network-structured datasets, i.e., big data over networks. We model the underlying hypothesis, which relates data points to labels, as a graph signal, defined over some graph (network) structure intrinsic to the dataset. Follo…

Even though Deep Neural Networks (DNNs) are widely celebrated for their practical performance, they possess many intriguing properties related to depth that are difficult to explain both theoretically and intuitively. Understanding how weights in deep networks coordinate together across layers to form useful learners h…

Linear encoding of sparse vectors is widely popular, but is commonly data-independent -- missing any possible extra (but a priori unknown) structure beyond sparsity. In this paper we present a new method to learn linear encoders that adapt to data, while still performing well with the widely used $\ell_1$ decoder. The …

This is a report of our lessons learned building acoustic models from 1 Million hours of unlabeled speech, while labeled speech is restricted to 7,000 hours. We employ student/teacher training on unlabeled data, helping scale out target generation in comparison to confidence model based methods, which require a decoder…

This paper improves understanding of knowledge distillation and its effects.