FLOWGEN:快速和慢速图形生成
FLOWGEN: Fast and slow graph generation
摘要:
机器学习系统通常将相同的模型应用于简单和困难的情况。这与人类形成鲜明对比,人类倾向于根据问题的难度唤起快速(本能)或慢速(分析)思维,这一特性称为心理的双重过程理论。我们提出了FLOWGEN,图形生成模型的灵感来自双过程理论的心态,产生大图形增量。根据在当前步骤完成图形的难度,图形生成被路由到快速(较弱)或慢速(较强)模型。这些模块具有相同的架构,但参数数量不同,因此发电能力不同。在真实世界图上的实验表明,我们可以成功地生成类似于单个大型模型生成的图,同时速度快2倍。
英文摘要:
Machine learning systems typically apply the same model to both easy and tough cases. This is in stark contrast with humans, who tend to evoke either fast (instinctive) or slow (analytical) thinking depending on the problem difficulty, a property called the dual-process theory of mind. We present FLOWGEN, a graph-generation model inspired by the dual-process theory of mind that generates large graphs incrementally. Depending on the difficulty of completing the graph at the current step, graph generation is routed to either a fast (weaker) or a slow (stronger) model. These modules have identical architectures, but vary in the number of parameters and consequently differ in generative power. Experiments on real-world graphs show that ours can successfully generate graphs similar to those generated by a single large model, while being up to 2x faster.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。