中文
相关论文

相关论文: Attention Weighted Mixture of Experts with Contras…

200 篇论文

In parameter-efficient fine-tuning, mixture-of-experts (MoE), which involves specializing functionalities into different experts and sparsely activating them appropriately, has been widely adopted as a promising approach to trade-off…

机器学习 · 计算机科学 2025-08-29 Jinyuan Feng , Chaopeng Wei , Tenghai Qiu , Tianyi Hu , Zhiqiang Pu

Understanding consumer choice is fundamental to marketing and management research, as firms increasingly seek to personalize offerings and optimize customer engagement. Traditional choice modeling frameworks, such as multinomial logit (MNL)…

机器学习 · 计算机科学 2025-03-11 Diego Vallarino

Product search is the most common way for people to satisfy their shopping needs on e-commerce websites. Products are typically annotated with one of several broad categorical tags, such as "Clothing" or "Electronics", as well as…

机器学习 · 计算机科学 2021-03-03 Zhuojian Xiao , Yunjiang jiang , Guoyu Tang , Lin Liu , Sulong Xu , Yun Xiao , Weipeng Yan

Mixture-of-Experts (MoE) models are designed to enhance the efficiency of large language models (LLMs) without proportionally increasing the computational demands. However, their deployment on edge devices still faces significant challenges…

机器学习 · 计算机科学 2024-08-21 Shuzhang Zhong , Ling Liang , Yuan Wang , Runsheng Wang , Ru Huang , Meng Li

Face alignment consists of aligning a shape model on a face image. It is an active domain in computer vision as it is a preprocessing for a number of face analysis and synthesis applications. Current state-of-the-art methods already perform…

计算机视觉与模式识别 · 计算机科学 2019-10-22 Estephe Arnaud , Arnaud Dapogny , Kevin Bailly

Mixture-of-Experts (MoE) models mostly use a router to assign tokens to specific expert modules, activating only partial parameters and often outperforming dense models. We argue that the separation between the router's decision-making and…

计算与语言 · 计算机科学 2025-06-02 Ang Lv , Ruobing Xie , Yining Qian , Songhao Wu , Xingwu Sun , Zhanhui Kang , Di Wang , Rui Yan

Mixture-of-Experts (MoE) networks have been proposed as an efficient way to scale up model capacity and implement conditional computing. However, the study of MoE components mostly focused on the feedforward layer in Transformer…

计算与语言 · 计算机科学 2022-10-12 Xiaofeng Zhang , Yikang Shen , Zeyu Huang , Jie Zhou , Wenge Rong , Zhang Xiong

Mixture-of-Experts (MoE) Large Language Models (LLMs) efficiently scale-up the model while keeping relatively low inference cost. As MoE models only activate part of the experts, related work has proposed expert prediction and caching…

计算与语言 · 计算机科学 2025-11-17 Shien Zhu , Samuel Bohl , Robin Oester , Gustavo Alonso

Modeling feature interactions is essential for accurate click-through rate (CTR) prediction in advertising systems. Recent studies have adopted the Mixture-of-Experts (MoE) approach to improve performance by ensembling multiple feature…

信息检索 · 计算机科学 2025-09-16 Jiancheng Wang , Mingjia Yin , Hao Wang , Enhong Chen

Optimizing various wireless user tasks poses a significant challenge for networking systems because of the expanding range of user requirements. Despite advancements in Deep Reinforcement Learning (DRL), the need for customized optimization…

网络与互联网体系结构 · 计算机科学 2024-02-16 Hongyang Du , Guangyuan Liu , Yijing Lin , Dusit Niyato , Jiawen Kang , Zehui Xiong , Dong In Kim

A useful strategy to deal with complex classification scenarios is the "divide and conquer" approach. The mixture of experts (MOE) technique makes use of this strategy by joinly training a set of classifiers, or experts, that are…

机器学习 · 计算机科学 2014-05-30 Billy Peralta

In mobile edge computing (MEC) networks, mobile users generate diverse machine learning tasks dynamically over time. These tasks are typically offloaded to the nearest available edge server, by considering communication and computational…

机器学习 · 计算机科学 2025-03-26 Hongbo Li , Lingjie Duan

Mixture-of-Experts (MoE) models have shown remarkable capability in instruction tuning, especially when the number of tasks scales. However, previous methods simply merge all training tasks (e.g. creative writing, coding, and mathematics)…

计算与语言 · 计算机科学 2024-06-18 Tong Zhu , Daize Dong , Xiaoye Qu , Jiacheng Ruan , Wenliang Chen , Yu Cheng

The sparsely activated mixture of experts (MoE) model presents a promising alternative to traditional densely activated (dense) models, enhancing both quality and computational efficiency. However, training MoE models from scratch demands…

计算机视觉与模式识别 · 计算机科学 2024-06-10 Xingkui Zhu , Yiran Guan , Dingkang Liang , Yuchao Chen , Yuliang Liu , Xiang Bai

Preference-based reinforcement learning offers a scalable alternative to manual reward engineering by learning reward structures from comparative feedback. However, large-scale preference datasets, whether collected from crowdsourced…

机器人学 · 计算机科学 2026-05-04 Ziqin Yuan , Ruiqi Wang , Dezhong Zhao , Baijian Yang , Byung-Cheol Min

Mixtures-of-Experts (MoE) are conditional mixture models that have shown their performance in modeling heterogeneity in data in many statistical learning approaches for prediction, including regression and classification, as well as for…

统计方法学 · 统计学 2019-07-17 Bao Tuyen Huynh , Faicel Chamroukhi

The first-stage retrieval aims to retrieve a subset of candidate documents from a huge collection both effectively and efficiently. Since various matching patterns can exist between queries and relevant documents, previous work tries to…

信息检索 · 计算机科学 2023-11-07 Yinqiong Cai , Yixing Fan , Keping Bi , Jiafeng Guo , Wei Chen , Ruqing Zhang , Xueqi Cheng

Due to the inherent difficulty in modeling phonetic similarities across different languages, code-switching speech recognition presents a formidable challenge. This study proposes a Collaborative-MoE, a Mixture of Experts (MoE) model that…

计算与语言 · 计算机科学 2024-09-06 Hukai Huang , Jiayan Lin , Kaidi Wang , Yishuang Li , Wenhao Guan , Lin Li , Qingyang Hong

As the era of big data arrives, traditional artificial intelligence algorithms have difficulty processing the demands of massive and diverse data. Mixture of experts (MoE) has shown excellent performance and broad application prospects.…

机器学习 · 计算机科学 2025-01-29 Wensheng Gan , Zhenyao Ning , Zhenlian Qi , Philip S. Yu

We propose Preferential MoE, a novel human-ML mixture-of-experts model that augments human expertise in decision making with a data-based classifier only when necessary for predictive performance. Our model exhibits an interpretable gating…

机器学习 · 计算机科学 2021-01-15 Melanie F. Pradier , Javier Zazo , Sonali Parbhoo , Roy H. Perlis , Maurizio Zazzi , Finale Doshi-Velez
‹ 上一页 1 2 3 10 下一页 ›