GitHub

Official Code for "Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Models" (To Appear in WMT 2022)

├── readme.md ├── requirements.txt ├── scripts # Scripts with all the variants of the commands + default hyperparameter values │ ├── confidence_estimation.sh # logging the confidence statistics │ ├── ...
INSPIRE

Graphs of Three-body Wave Functions

Part of Proceedings, 9th International IUPAP Conference on Few Body Problems in Physics (FB9): Eugene, Oregon, August 17-23, 1980, 61-73 Plots of the numerical solutions of the Faddeev equations in ...
IEEE

False Negative Sample Detection for Graph Contrastive Learning

Abstract: Recently, self-supervised learning has shown great potential in Graph Neural Networks (GNNs) through contrastive learning, which aims to learn discriminative features for each node without ...
GitHub

Which Modality should I use -- Text, Motif, or Image? : Understanding Graphs with Large Language Models

conda create --name graphllm python==3.10.12 conda activate graphllm pip install torch pip install openai pip install torch_geometric pip install pyg_lib torch ...
IEEE

Graph Meta Transfer Network for Heterogeneous Few-Shot Hyperspectral Image Classification

Abstract: Since obtaining labeled hyperspectral images (HSIs) is difficult and time-consuming, the shortage of training samples has always been a challenge for HSI classification. In practical ...