Zobrazeno 1 - 10
of 348
pro vyhledávání: '"Zhu, Weiyao"'
Measuring the value of individual samples is critical for many data-driven tasks, e.g., the training of a deep learning model. Recent literature witnesses the substantial efforts in developing data valuation methods. The primary data valuation method
Externí odkaz:
http://arxiv.org/abs/2406.02612
Sample weighting is widely used in deep learning. A large number of weighting methods essentially utilize the learning difficulty of training samples to calculate their weights. In this study, this scheme is called difficulty-based weighting. Two imp
Externí odkaz:
http://arxiv.org/abs/2301.04850
As learning difficulty is crucial for machine learning (e.g., difficulty-based weighting learning strategies), previous literature has proposed a number of learning difficulty measures. However, no comprehensive investigation for learning difficulty
Externí odkaz:
http://arxiv.org/abs/2205.07427
Publikováno v:
In Information Sciences August 2024 677
Publikováno v:
In Marine and Petroleum Geology October 2024 168
Publikováno v:
In Heliyon 30 June 2024 10(12)
Publikováno v:
In International Journal of Hydrogen Energy 12 June 2024 70:136-145
Autor:
Pan, Bin, Yin, Xia, Yang, Zhengru, Ghanizadeh, Amin, Debuhr, Chris, Clarkson, Christopher R., Gou, Feifei, Zhu, Weiyao, Ju, Yang, Iglauer, Stefan
Publikováno v:
In Applied Energy 1 June 2024 363
Publikováno v:
In Petroleum Research June 2024 9(2):165-175
A common assumption in machine learning is that samples are independently and identically distributed (i.i.d). However, the contributions of different samples are not identical in training. Some samples are difficult to learn and some samples are noi
Externí odkaz:
http://arxiv.org/abs/2106.05522