Equilibrium Aggregation：通过优化编码集合
Equilibrium Aggregation: Encoding Sets via Optimization
摘要：
处理神经网络中的集合或其他无序的、潜在可变大小的输入通常通过将多个输入张量聚合成单个表示来处理。虽然已经存在一些聚合方法，从简单的总和池到多头注意力，但从理论和经验角度来看，它们的代表性都很有限。在寻找一个更强大的聚合策略时，我们提出了一种基于优化的方法，称为均衡聚合。我们发现，许多现有的聚合方法可以恢复为特殊情况下的均衡聚合，它是证明更有效的在一些重要的情况下。平衡聚合可以在许多现有的架构和应用程序中用作直接替代。我们验证了它的效率在三个不同的任务：中位数估计，类计数，和分子性质预测。在所有实验中，均衡聚合比我们测试的其他聚合技术实现了更高的性能。
英文摘要：
Processing sets or other unordered, potentially variable-sized inputs in neural networks is usually handled by aggregating a number of input tensors into a single representation. While a number of aggregation methods already exist from simple sum pooling to multi-head attention, they are limited in their representational power both from theoretical and empirical perspectives. On the search of a principally more powerful aggregation strategy, we propose an optimization-based method called Equilibrium Aggregation. We show that many existing aggregation methods can be recovered as special cases of Equilibrium Aggregation and that it is provably more efficient in some important cases. Equilibrium Aggregation can be used as a drop-in replacement in many existing architectures and applications. We validate its efficiency on three different tasks: median estimation, class counting, and molecular property prediction. In all experiments, Equilibrium Aggregation achieves higher performance than the other aggregation techniques we test.
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。
