We propose Automatic Feature Explanation using Contrasting Concepts (FAL...
Image-text contrastive models such as CLIP are useful for a variety of
d...
Artificial intelligence (AI) has seen a tremendous surge in capabilities...
We observe that the mapping between an image's representation in one mod...
Recently, self-supervised learning (SSL) was shown to be vulnerable to
p...
Differential privacy (DP) is by far the most widely accepted framework f...
An oft-cited challenge of federated learning is the presence of
heteroge...
Personalized text generation has broad industrial applications, such as
...
Free-text rationales aim to explain neural language model (LM) behavior ...
An oft-cited challenge of federated learning is the presence of data
het...
Neural language models' (NLMs') reasoning processes are notoriously hard...
The practice of applying several local updates before aggregation across...
We propose an autoregressive entity linking model, that is trained with ...
We consider two federated learning algorithms for training partially
per...
Self-supervised learning methods have shown impressive results in downst...
While neural networks have shown remarkable success on classification ta...
An extractive rationale explains a language model's (LM's) prediction on...
Exponential tilting is a technique commonly used in fields such as
stati...
Large neural networks are impractical to deploy on mobile devices due to...
Quantization of the parameters of machine learning models, such as deep
...
Empirical risk minimization (ERM) is typically designed to perform well ...
Federated learning aims to jointly learn statistical models over massive...
We study the optimization problem for decomposing d dimensional
fourth-o...
Federated learning involves training statistical models in massive,
hete...
In recent years, Generative Adversarial Networks (GANs) have drawn a lot...
The burgeoning field of federated learning involves training machine lea...
In this short note, we consider the problem of solving a min-max zero-su...
Generative Adversarial Networks (GANs) are one of the most practical
str...
Federated learning poses new statistical and systems challenges in train...