English
Related papers

Related papers: Sparse Mixture-of-Experts are Domain Generalizable…

200 papers

Machine learning (ML) has demonstrated significant promise in accelerating drug design. Active ML-guided optimization of therapeutic molecules typically relies on a surrogate model predicting the target property of interest. The model…

Domain generalization (DG) seeks predictors which perform well on unseen test distributions by leveraging data drawn from multiple related training distributions or domains. To achieve this, DG is commonly formulated as an average- or…

We present a systematic study of domain generalization (DG) for tiny neural networks. This problem is critical to on-device machine learning applications but has been overlooked in the literature where research has been merely focused on…

Computer Vision and Pattern Recognition · Computer Science 2022-11-09 Kaiyang Zhou , Yuanhan Zhang , Yuhang Zang , Jingkang Yang , Chen Change Loy , Ziwei Liu

The interpretability of Mixture-of-Experts (MoE) models, especially those with heterogeneous designs, remains underexplored. Existing attribution methods for dense models fail to capture dynamic routing-expert interactions in sparse MoE…

Computation and Language · Computer Science 2025-06-12 Junzhuo Li , Bo Wang , Xiuze Zhou , Peijie Jiang , Jia Liu , Xuming Hu

Deep learning on graphs has shown remarkable success across numerous applications, including social networks, bio-physics, traffic networks, and recommendation systems. Regardless of their successes, current methods frequently depend on the…

Machine Learning · Computer Science 2025-09-25 Itay Niv , Neta Rabin

Object detectors have achieved remarkable performance in many applications; however, these deep learning models are typically designed under the i.i.d. assumption, meaning they are trained and evaluated on data sampled from the same…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Sara Al-Emadi , Yin Yang , Ferda Ofli

Sparsely Mixture of Experts (MoE) has received great interest due to its promising scaling capability with affordable computational overhead. MoE converts dense layers into sparse experts, and utilizes a gated routing network to make…

Computation and Language · Computer Science 2022-07-20 Yuan Xie , Shaohan Huang , Tianyu Chen , Furu Wei

Mixture-of-Experts (MoE) architectures have become the dominant choice for scaling Large Language Models (LLMs), activating only a subset of parameters per token. While MoE architectures are primarily adopted for computational efficiency,…

Computation and Language · Computer Science 2026-05-19 Jeremy Herbst , Stefan Wermter , Jae Hee Lee

Although supervised deep stereo matching networks have made impressive achievements, the poor generalization ability caused by the domain gap prevents them from being applied to real-life scenarios. In this paper, we propose to leverage the…

Computer Vision and Pattern Recognition · Computer Science 2022-04-04 Biyang Liu , Huimin Yu , Guodong Qi

Recognition across domains has recently become an active topic in the research community. However, it has been largely overlooked in the problem of recognition in new unseen domains. Under this condition, the delivered deep network models…

Computer Vision and Pattern Recognition · Computer Science 2020-04-15 Thanh-Dat Truong , Chi Nhan Duong , Khoa Luu , Minh-Triet Tran , Ngan Le

Unified image generation and editing models suffer from severe task interference in dense diffusion transformers architectures, where a shared parameter space must compromise between conflicting objectives (e.g., local editing v.s.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Yu Xu , Hongbin Yan , Juan Cao , Yiji Cheng , Tiankai Hang , Runze He , Zijin Yin , Shiyi Zhang , Yuxin Zhang , Jintao Li , Chunyu Wang , Qinglin Lu , Tong-Yee Lee , Fan Tang

Domain generalization (DG) aims to improve the generalizability of computer vision models toward distribution shifts. The mainstream DG methods focus on learning domain invariance, however, such methods overlook the potential inherent in…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Shaocong Long , Qianyu Zhou , Xiangtai Li , Chenhao Ying , Yunhai Tong , Lizhuang Ma , Yuan Luo , Dacheng Tao

Federated learning (FL) is a collaborative machine learning approach that enables multiple clients to train models without sharing their private data. With the rise of deep learning, large-scale models have garnered significant attention…

Machine Learning · Computer Science 2025-09-09 Ziwei Zhan , Wenkuan Zhao , Yuanqing Li , Weijie Liu , Xiaoxi Zhang , Chee Wei Tan , Chuan Wu , Deke Guo , Xu Chen

Domain generalization (DG) aims to adapt a model using one or multiple source domains to ensure robust performance in unseen target domains. Recently, Parameter-Efficient Fine-Tuning (PEFT) of foundation models has shown promising results…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Seokju Yun , Seunghye Chae , Dongheon Lee , Youngmin Ro

Learning effective embedding has been proved to be useful in many real-world problems, such as recommender systems, search ranking and online advertisement. However, one of the challenges is data sparsity in learning large-scale item…

Machine Learning · Computer Science 2019-05-27 Yi Ouyang , Bin Guo , Xing Tang , Xiuqiang He , Jian Xiong , Zhiwen Yu

In this study, we address the gradient-based domain generalization problem, where predictors aim for consistent gradient directions across different domains. Existing methods have two main challenges. First, minimization of gradient…

Machine Learning · Computer Science 2025-07-22 Khoi Do , Duong Nguyen , Nam-Khanh Le , Quoc-Viet Pham , Binh-Son Hua , Won-Joo Hwang

In the generalized zero-shot learning, synthesizing unseen data with generative models has been the most popular method to address the imbalance of training data between seen and unseen classes. However, this method requires that the unseen…

Computer Vision and Pattern Recognition · Computer Science 2020-02-04 Xinsheng Wang , Shanmin Pang , Jihua Zhu

The evolution of biological neural systems has led to both modularity and sparse coding, which enables energy efficiency and robustness across the diversity of tasks in the lifespan. In contrast, standard neural networks rely on dense,…

Machine Learning · Computer Science 2025-02-13 Sagi Shaier , Francisco Pereira , Katharina von der Wense , Lawrence E Hunter , Matt Jones

As a recent noticeable topic, domain generalization (DG) aims to first learn a generic model on multiple source domains and then directly generalize to an arbitrary unseen target domain without any additional adaption. In previous DG…

Computer Vision and Pattern Recognition · Computer Science 2022-02-17 Yue Wang , Lei Qi , Yinghuan Shi , Yang Gao

Domain Generalization (DG) aims to learn models whose performance remains high on unseen domains encountered at test-time by using data from multiple related source domains. Many existing DG algorithms reduce the divergence between source…

Machine Learning · Computer Science 2022-06-27 Akshay Mehra , Bhavya Kailkhura , Pin-Yu Chen , Jihun Hamm
‹ Prev 1 8 9 10 Next ›