164 citations · 172 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024★ 5 cited
Meta-GCN: A Dynamically Weighted Loss Minimization Method for Dealing with the Data Imbalance in Graph Neural Networks
Mahdi Mohammadizadeh, Arash Mozhdehi, Yani Ioannou +1
Although many real-world applications, such as disease prediction, and fault detection suffer from class imbalance, most existing graph-based classification methods ignore the skew…
cs.LG2017★ 164 cited
Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks
Urs Köster, Tristan J. Webb, Xin Wang +11
Deep neural networks are commonly developed and trained in 32-bit floating point format. Significant gains in performance and energy efficiency could be realized by training and in…