论文标题
紧急沟通中的结构归纳偏见
Structural Inductive Biases in Emergent Communication
论文作者
论文摘要
为了交流，人类将思想及其属性的复杂表示形式化为一个单词或句子。我们通过开发图形参考游戏来调查人工代理中代表性学习的影响。我们从经验上表明，与单词和序列模型相比，通过图神经网络参数参数的代理会发展出更具组成性的语言，这使他们可以系统地将其概括为熟悉功能的新组合。
In order to communicate, humans flatten a complex representation of ideas and their attributes into a single word or a sentence. We investigate the impact of representation learning in artificial agents by developing graph referential games. We empirically show that agents parametrized by graph neural networks develop a more compositional language compared to bag-of-words and sequence models, which allows them to systematically generalize to new combinations of familiar features.
