点击上方，选择星标或置顶，每天给你送干货！

阅读大概需要5分钟

跟随小博主，每天进步一丢丢

来自：RUC AI Box公众号

欢迎大家关注！

导读

下面论文列表为本小组同学推荐和整理，关于论文细节请联系论文作者。内容涵盖以下研究方向：迁移学习、图神经网络。

本周论文推荐

 1  

 图神经网络 

• Graph Transformer Networks - Seongjun Yun, Minbyul Jeong, Raehyun Kim, Jaewoo Kang, Hyunwoo Kim - NIPS 2019

• GraphZoom: A Multi-level Spectral Approach for Accurate and Scalable Graph Embedding - Chenhui Deng, Zhiqiang Zhao, Yongyu Wang, Zhiru Zhang, Zhuo Feng - ICLR 2020

• Strategies for Pre-training Graph Neural Networks - Weihua Hu*, Bowen Liu*, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay Pande, Jure Leskovec - ICLR 2020

• Contrastive Learning of Structured World Models - Thomas Kipf, Elise van der Pol, Max Welling - ICLR2020

• The Logical Expressiveness of Graph Neural Networks - Pablo Barceló, Egor V. Kostylev, Mikael Monet, Jorge Pérez, Juan Reutter, Juan Pablo Silva - ICLR2020

• Geom-GCN: Geometric Graph Convolutional Networks - Hongbin Pei, Bingzhe Wei, Kevin Chen-Chuan Chang, Yu Lei, Bo Yang - ICLR2020

• Hyper-SAGNN: a self-attention based graph neural network for hypergraphs - Ruochi Zhang, Yuesong Zou, Jian Ma - ICLR2020

• Measuring and Improving the Use of Graph Information in Graph Neural Networks - Yifan Hou, Jian Zhang, James Cheng, Kaili Ma, Richard T. B. Ma, Hongzhi Chen, Ming-Chang Yang - ICLR 2020

• Adaptive Structural Fingerprints for Graph Attention Networks - Kai Zhang, Yaokang Zhu, Jun Wang, Jie Zhang - ICLR 2020

• Memory-Based Graph Networks - Amir hosein Khasahmadi, Kaveh Hassani, Parsa Moradi, Leo Lee, Quaid Morris - ICLR 2020

 2  

 迁移学习 

• Sharing Knowledge in Multi-Task Deep Reinforcement Learning - Carlo DEramo, Davide Tateo, Andrea Bonarini, Marcello Restelli, Jan Peters - ICLR 2020

• Masked Based Unsupervised Content Transfer - Ron Mokady, Sagie Benaim, Lior Wolf, Amit Bermano - ICLR 2020

• Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification - Yixiao Ge, Dapeng Chen, Hongsheng Li - ICLR 2020

• Understanding and Improving Information Transfer in Multi-Task Learning - Sen Wu, Hongyang Zhang, Christopher Re - ICLR 2020

本期编辑：王辉

方便交流学习，备注：昵称-学校（公司）-方向，进入DL&NLP交流群。

方向有很多：机器学习、深度学习，python，情感分析、意见挖掘、句法分析、机器翻译、人机对话、知识图谱、语音识别等。

记得备注呦

推荐阅读：

【ACL 2019】腾讯AI Lab解读三大前沿方向及20篇入选论文

【一分钟论文】IJCAI2019 | Self-attentive Biaffine Dependency  Parsing

【一分钟论文】 NAACL2019-使用感知句法词表示的句法增强神经机器翻译

【一分钟论文】Semi-supervised Sequence Learning半监督序列学习

【一分钟论文】Deep Biaffine Attention for Neural Dependency Parsing

详解Transition-based Dependency parser基于转移的依存句法解析器

经验 | 初入NLP领域的一些小建议

学术 | 如何写一篇合格的NLP论文

干货 | 那些高产的学者都是怎样工作的？

一个简单有效的联合模型

近年来NLP在法律领域的相关研究工作

让更多的人知道你“在看”