Lymphocyte
发表于 2025-3-28 15:00:39
Rejection Ensembles with Online Calibrationnt. One promising approach for optimizing resource consumption is rejection ensembles. Rejection ensembles combine a small model deployed to an edge device with a large model deployed in the cloud with a rejector tasked to determine the most suitable model for a given input. Due to its novelty, exis
白杨
发表于 2025-3-28 19:33:32
http://reply.papertrans.cn/63/6206/620540/620540_42.png
旅行路线
发表于 2025-3-28 23:01:13
http://reply.papertrans.cn/63/6206/620540/620540_43.png
hemorrhage
发表于 2025-3-29 04:16:26
http://reply.papertrans.cn/63/6206/620540/620540_44.png
策略
发表于 2025-3-29 08:46:10
Interpetable Target-Feature Aggregation for Multi-task Learning Based on Bias-Variance Analysisformance. Previous works have proposed approaches to MTL that can be divided into feature learning, focused on the identification of a common feature representation, and task clustering, where similar tasks are grouped together. In this paper, we propose an MTL approach at the intersection between t
ALB
发表于 2025-3-29 14:46:20
The Simpler The Better: An Entropy-Based Importance Metric to Reduce Neural Networks’ Depthmpler downstream tasks, which do not necessarily require a large model’s complexity. Motivated by the awareness of the ever-growing AI environmental impact, we propose an efficiency strategy that leverages prior knowledge transferred by large models. Simple but effective, we propose a method relying
使纠缠
发表于 2025-3-29 16:04:37
Towards Few-Shot Self-explaining Graph Neural Networksy in critical domains such as medicine. A promising approach is the self-explaining method, which outputs explanations along with predictions. However, existing self-explaining models require a large amount of training data, rendering them unavailable in few-shot scenarios. To address this challenge
条约
发表于 2025-3-29 23:04:20
http://reply.papertrans.cn/63/6206/620540/620540_48.png
Germinate
发表于 2025-3-30 02:42:49
http://reply.papertrans.cn/63/6206/620540/620540_49.png
格言
发表于 2025-3-30 05:52:37
http://reply.papertrans.cn/63/6206/620540/620540_50.png