Related papers: InfoShape: Task-Based Neural Data Shaping via Mutu…

Cloud computing enables users to process and store data remotely on high-performance computers and servers by sharing data over the Internet. However, transferring data to clouds causes unavoidable privacy concerns. Here, we present a…

Neural networks, with the capability to provide efficient predictive models, have been widely used in medical, financial, and other fields, bringing great convenience to our lives. However, the high accuracy of the model requires a large…

Traditional machine learning (ML) algorithms, such as multiple regression, require human analysts to make decisions on how to treat the data. These decisions can make the model building process subjective and difficult to replicate for…

We introduce a parameterization method called Neural Bayes which allows computing statistical quantities that are in general difficult to compute and opens avenues for formulating new objectives for unsupervised representation learning.…

Decentralized learning with private data is a central problem in machine learning. We propose a novel distillation-based decentralized learning technique that allows multiple agents with private non-iid data to learn from each other,…

Deep learning systems have been reported to acheive state-of-the-art performances in many applications, and one of the keys for achieving this is the existence of well trained classifiers on benchmark datasets which can be used as backbone…

Most existing deep multi-task learning models are based on parameter sharing, such as hard sharing, hierarchical sharing, and soft sharing. How choosing a suitable sharing mechanism depends on the relations among the tasks, which is not…

In this paper, we assess the viability of transformer models in end-to-end InfoSec settings, in which no intermediate feature representations or processing steps occur outside the model. We implement transformer models for two distinct…

Learning-based lossy image compression usually involves the joint optimization of rate-distortion performance. Most existing methods adopt spatially invariant bit length allocation and incorporate discrete entropy approximation to constrain…

Machine learning (ML) models often require large amounts of data to perform well. When the available data is limited, model trainers may need to acquire more data from external sources. Often, useful data is held by private entities who are…

In the paradigm of multi-task learning, mul- tiple related prediction tasks are learned jointly, sharing information across the tasks. We propose a framework for multi-task learn- ing that enables one to selectively share the information…

In psychotherapy interactions, the quality of a session is assessed by codifying the communicative behaviors of participants during the conversation through manual observation and annotation. Developing computational approaches for…

We aim to train a multi-task model such that users can adjust the desired compute budget and relative importance of task performances after deployment, without retraining. This enables optimizing performance for dynamically varying user…

Masked autoencoders (MAEs) represent a prominent self-supervised learning paradigm in computer vision. Despite their empirical success, the underlying mechanisms of MAEs remain insufficiently understood. Recent studies have attempted to…

The widespread adoption of encryption in network protocols has significantly improved the overall security of many Internet applications. However, these protocols cannot prevent network side-channel leaks -- leaks of sensitive information…

Frequent metering of electricity consumption is crucial for demand side management in smart grids. However, metered data can be processed fairly easily by employing well-established nonintrusive appliance load monitoring techniques to infer…

In the one-class recommendation problem, it's required to make recommendations basing on users' implicit feedback, which is inferred from their action and inaction. Existing works obtain representations of users and items by encoding…

We show that the influence of a subset of the training samples can be removed -- or "forgotten" -- from the weights of a network trained on large-scale image classification tasks, and we provide strong computable bounds on the amount of…

Multivariate pattern analyses approaches in neuroimaging are fundamentally concerned with investigating the quantity and type of information processed by various regions of the human brain; typically, estimates of classification accuracy…

Systems neuroscience relies on two complementary views of neural data, characterized by single neuron tuning curves and analysis of population activity. These two perspectives combine elegantly in neural latent variable models that…