Related papers: NURD: Negative-Unlabeled Learning for Online Datac…

With the success of pre-trained visual-language (VL) models such as CLIP in visual representation tasks, transferring pre-trained models to downstream tasks has become a crucial paradigm. Recently, the prompt tuning paradigm, which draws…

Recently, graph neural networks (GNNs) have shown its unprecedented success in many graph-related tasks. However, GNNs face the label scarcity issue as other neural networks do. Thus, recent efforts try to pre-train GNNs on a large-scale…

Interactive time responses are a crucial requirement for users analyzing large amounts of data. Such analytical queries are typically run in a distributed setting, with data being sharded across thousands of nodes for high throughput.…

Training language models to learn from human instructions for zero-shot cross-task generalization has attracted much attention in NLP communities. Recently, instruction tuning (IT), which fine-tunes a pre-trained language model on a massive…

Learning with noisy labels (LNL) is essential for training deep neural networks with imperfect data. Meta-learning approaches have achieved success by using a clean unbiased labeled set to train a robust model. However, this approach…

Language model pre-training has proven to be useful in many language understanding tasks. In this paper, we investigate whether it is still helpful to add the self-training method in the pre-training step and the fine-tuning step. Towards…

Deep Neural Networks (DNNs) have become an essential component in many application domains including web-based services. A variety of these services require high throughput and (close to) real-time features, for instance, to respond or…

In this article, we address the problem of federated learning in the presence of stragglers. For this problem, a coded federated learning framework has been proposed, where the central server aggregates gradients received from the…

Ongoing developments in neural network models are continually advancing the state of the art in terms of system accuracy. However, the predicted labels should not be regarded as the only core output; also important is a well-calibrated…

Failed workloads that consumed significant computational resources in time and space affect the efficiency of data centers significantly and thus limit the amount of scientific work that can be achieved. While the computational power has…

Upside Down Reinforcement Learning (UDRL) is a promising framework for solving reinforcement learning problems which focuses on learning command-conditioned policies. In this work, we extend UDRL to the task of learning a…

In-context learning (ICL) enables large language models (LLMs) to perform new tasks using only a few demonstrations. However, in Named Entity Recognition (NER), existing ICL methods typically rely on task-agnostic semantic similarity for…

Sample selection is a prevalent method in learning with noisy labels, where small-loss data are typically considered as correctly labeled data. However, this method may not effectively identify clean hard examples with large losses, which…

Deep neural networks (DNNs) offer a means of addressing the challenging task of clustering high-dimensional data. DNNs can extract useful features, and so produce a lower dimensional representation, which is more amenable to clustering…

A key challenge for machine intelligence is to learn new visual concepts without forgetting the previously acquired knowledge. Continual learning is aimed towards addressing this challenge. However, there is a gap between existing…

Offline Reinforcement Learning (RL) aims to learn effective policies from a static dataset without requiring further agent-environment interactions. However, its practical adoption is often hindered by the need for explicit reward…

Distributed computing enables large-scale computation tasks to be processed over multiple workers in parallel. However, the randomness of communication and computation delays across workers causes the straggler effect, which may degrade the…

A fundamental question in designing lossy data compression schemes is how well one can do in comparison with the rate-distortion function, which describes the known theoretical limits of lossy compression. Motivated by the empirical success…

Deep Neural Networks (DNNs) have become key components of many safety-critical applications such as autonomous driving and medical diagnosis. However, DNNs have been shown suffering from poor robustness because of their susceptibility to…

Ultra reliable low latency communications (URLLC) is a new service class introduced in 5G which is characterized by strict reliability $(1-10^{-5})$ and low latency requirements (1 ms). To meet these requisites, several strategies like…