.png){kind=icon}
返回
Memory-efficient DRASiW Models
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2024.128443.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Weightless Neural Networks (WNN) are ideal for Federated Learning due to their robustness and computational efficiency. These scenarios require models with a small memory footprint and the ability to aggregate knowledge from multiple models. In this work, we demonstrate the effectiveness of using Bloom filter variations to implement DRASiW models-an adaptation of WNN that records both the presence and frequency of patterns-with minimized memory usage. Across various datasets, DRASiW models show competitive performance compared to models like Random Forest, k-Nearest Neighbors, Multi-layer Perceptron, and Support Vector Machines, with an acceptable space trade-off. Furthermore, our findings indicate that Bloom filter variations, such as Count Min Sketch, can reduce the memory footprint of DRASiW models by up to 27% while maintaining performance and enabling distributed and federated learning strategies.
Keyword:
Bloom filters
DRASiW
Knowledge aggregation
Weightless neural network
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Multilingual part-of-speech tagging with weightless neural networks基于失重神经网络的多语言词性标注.png)
NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏Analysis and assessment of ship collision accidents using Fault Tree and Multiple Correspondence Analysis基于故障树和多重对应分析的船舶碰撞事故分析与评估
PREAI
分享收藏
Predicting Adhesion Energies of Late Transition Metal Nanoparticles to Oxide Support Surfaces Using Oxide Reducibility and Metal Oxophilicity: Toward Predicting Catalyst Performance利用氧化物可还原性和金属亲氧性预测晚期过渡金属纳米颗粒在氧化物载体表面的粘附能：迈向预测催化剂性能ACS CATALYSIS
ACS CATALYSISIF13.1
PREAI
分享收藏
查看更多内容