Related papers: Theoretically Guaranteed Distribution Adaptable Le…

Transfer learning aims to learn robust classifiers for the target domain by leveraging knowledge from a source domain. Since the source and the target domains are usually from different distributions, existing methods mainly focus on…

There is an increasing need to determine whether inputs are out-of-distribution (\emph{OOD}) for safely deploying machine learning models in the open world scenario. Typical neural classifiers are based on the closed world assumption, where…

Conformal prediction is a distribution-free uncertainty quantification method that has gained popularity in the machine learning community due to its finite-sample guarantees and ease of use. Its most common variant, dubbed split conformal…

Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or on the existence of a stronger model able to solve the problem. However,…

Open-world classification systems should discern out-of-distribution (OOD) data whose labels deviate from those of in-distribution (ID) cases, motivating recent studies in OOD detection. Advanced works, despite their promising progress, may…

Tabular learning transforms raw features into optimized spaces for downstream tasks, but its effectiveness deteriorates under distribution shifts between training and testing data. We formalize this challenge as the Distribution Shift…

Deep learning-based domain adaptation (DA) methods have shown strong performance by learning transferable representations. However, their reliance on mini-batch training limits global distribution modeling, leading to unstable alignment and…

Graph Domain Adaptation (GDA) aims to bridge distribution shifts between domains by transferring knowledge from well-labeled source graphs to given unlabeled target graphs. One promising recent approach addresses graph transfer by…

The wireless network is undergoing a trend from "onnection of things" to "connection of intelligence". With data spread over the communication networks and computing capability enhanced on the devices, distributed learning becomes a hot…

We propose a novel framework for incorporating unlabeled data into semi-supervised classification problems, where scenarios involving the minimization of either i) adversarially robust or ii) non-robust loss functions have been considered.…

While traditional Deep Learning (DL) optimization methods treat all training samples equally, Distributionally Robust Optimization (DRO) adaptively assigns importance weights to different samples. However, a significant gap exists between…

An essential problem in domain adaptation is to understand and make use of distribution changes across domains. For this purpose, we first propose a flexible Generative Domain Adaptation Network (G-DAN) with specific latent variables to…

Adaptivity is an important feature of data analysis---typically the choice of questions asked about a dataset depends on previous interactions with the same dataset. However, generalization error is typically bounded in a non-adaptive…

Domain adaptation (DA) is an important and emerging field of machine learning that tackles the problem occurring when the distributions of training (source domain) and test (target domain) data are similar but different. Current theoretical…

Graph neural networks have shown remarkable success in exploiting the spatial and temporal patterns on dynamic graphs. However, existing GNNs exhibit poor generalization ability under distribution shifts, which is inevitable in dynamic…

Machine Learning (ML) has been a foundational topic in artificial intelligence (AI), providing both theoretical groundwork and practical tools for its exciting advancements. From ResNet for visual recognition to Transformer for…

In this paper, we propose a novel self-supervised transfer learning method called \underline{\textbf{D}}istribution \underline{\textbf{M}}atching (DM), which drives the representation distribution toward a predefined reference distribution…

We propose Evolutionary Dynamic Loss (EDL), a framework that learns a transferable classification loss in the probability space using unlimited synthetic prediction-label pairs, without accessing real samples during the main loss…

The recent advances in deep transfer learning reveal that adversarial learning can be embedded into deep networks to learn more transferable features to reduce the distribution discrepancy between two domains. Existing adversarial domain…

The composition of pretraining data is a key determinant of foundation models' performance, but there is no standard guideline for allocating a limited computational budget across different data sources. Most current approaches either rely…