Adaptive Importance
Adaptive importance focuses on dynamically adjusting resource allocation or model parameters based on learned importance scores or contextual information, aiming to improve efficiency and performance in various machine learning tasks. Current research emphasizes adaptive sampling techniques, hyperparameter optimization strategies (like Loss Conditional Training), and the development of novel architectures such as Mixture-of-Experts models and adaptive low-rank adaptations to achieve this goal. This field is significant because it addresses critical challenges in scalability, efficiency, and robustness across diverse applications, including federated learning, reinforcement learning, and real-time processing on resource-constrained devices.
Papers
Adaptive Meta-learning-based Adversarial Training for Robust Automatic Modulation Classification
Amirmohammad Bamdad, Ali Owfi, Fatemeh Afghah
Adaptive Homophily Clustering: A Structure Homophily Graph Learning with Adaptive Filter for Hyperspectral Image
Yao Ding, Weijie Kang, Aitao Yang, Zhili Zhang, Junyang Zhao, Jie Feng, Danfeng Hong, Qinhe Zheng
Adaptive Context-Aware Multi-Path Transmission Control for VR/AR Content: A Deep Reinforcement Learning Approach
Shakil Ahmed, Saifur Rahman Sabuj, Ashfaq Khokhar
Boosting Private Domain Understanding of Efficient MLLMs: A Tuning-free, Adaptive, Universal Prompt Optimization Framework
Jiang Liu, Bolin Li, Haoyuan Li, Tianwei Lin, Wenqiao Zhang, Tao Zhong, Zhelun Yu, Jinghao Wei, Hao Cheng, Hao Jiang, Zheqi Lv, Juncheng Li, Siliang Tang, Yueting Zhuang
Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation
Derong Xu Xinhang Li, Ziheng Zhang, Zhenxi Lin, Zhihong Zhu, Zhi Zheng, Xian Wu, Xiangyu Zhao, Tong Xu, Enhong Chen
Neural Conformal Control for Time Series Forecasting
Ruipu Li, Alexander RodrÃguez