Related papers: HMOE: Hypernetwork-based Mixture of Experts for Do…
The well known domain shift issue causes model performance to degrade when deployed to a new target domain with different statistics to training. Domain adaptation techniques alleviate this, but need some instances from the target domain to…
Domain generalization is a technique aimed at enabling models to maintain high accuracy when applied to new environments or datasets (unseen domains) that differ from the datasets used in training. Generally, the accuracy of models trained…
The relentless scaling of deep learning models has led to unsustainable computational demands, positioning Mixture-of-Experts (MoE) architectures as a promising path towards greater efficiency. However, MoE models are plagued by two…
Graph Neural Networks (GNNs) have proven to be highly effective for node classification tasks across diverse graph structural patterns. Traditionally, GNNs employ a uniform global filter, typically a low-pass filter for homophilic graphs…
Domain generalization (DG) is proposed to deal with the issue of domain shift, which occurs when statistical differences exist between source and target domains. However, most current methods do not account for a common realistic scenario…
In deep learning, mixture-of-experts (MoE) activates one or few experts (sub-networks) on a per-sample or per-token basis, resulting in significant computation reduction. The recently proposed \underline{p}atch-level routing in…
The objective of domain generalization (DG) is to enable models to be robust against domain shift. DG is crucial for deploying vision-language models (VLMs) in real-world applications, yet most existing methods rely on domain labels that…
Machine learning models are intrinsically vulnerable to domain shift between training and testing data, resulting in poor performance in novel domains. Domain generalization (DG) aims to overcome the problem by leveraging multiple source…
Domain-specific adaptation is critical to maximizing the performance of pre-trained language models (PLMs) on one or multiple targeted tasks, especially under resource-constrained use cases, such as edge devices. However, existing methods…
To ensure the out-of-distribution (OOD) generalization performance, traditional domain generalization (DG) methods resort to training on data from multiple sources with different underlying distributions. And the success of those DG methods…
Mixture-of-Experts (MoE) Large Language Models (LLMs) face a trilemma of load imbalance, parameter redundancy, and communication overhead. We introduce a unified framework based on dynamic expert clustering and structured compression to…
Domain adaptation leverages the knowledge in one domain - the source domain - to improve learning efficiency in another domain - the target domain. Existing heterogeneous domain adaptation research is relatively well-progressed, but only in…
Domain generalization (DG), aiming at models able to work on multiple unseen domains, is a must-have characteristic of general artificial intelligence. DG based on single source domain training data is more challenging due to the lack of…
The problem of generalizing deep neural networks from multiple source domains to a target one is studied under two settings: When unlabeled target data is available, it is a multi-source unsupervised domain adaptation (UDA) problem,…
The mixture of experts (MoE) model is a versatile framework for predictive modeling that has gained renewed interest in the age of large language models. A collection of predictive ``experts'' is learned along with a ``gating function''…
As foundational models reshape scientific discovery, a bottleneck persists in dynamical system reconstruction (DSR): the ability to learn across system hierarchies. Many meta-learning approaches have been applied successfully to single…
Mixture-of-Experts (MoE) models offer immense capacity via sparsely gated expert subnetworks, yet adapting them to multiple domains without catastrophic forgetting remains an open challenge. Existing approaches either incur prohibitive…
The Mixture of Experts (MoE) paradigm provides a powerful way to decompose dense layers into smaller, modular computations often more amenable to human interpretation, debugging, and editability. However, a major challenge lies in the…
Distribution shift presents a significant challenge in machine learning, where models often underperform during the test stage when faced with a different distribution than the one they were trained on. This paper focuses on domain shifts,…
This paper focuses on domain generalization (DG), the task of learning from multiple source domains a model that generalizes well to unseen domains. A main challenge for DG is that the available source domains often exhibit limited…