网络环境下的多任务学习
Multi-Task Learning on Networks
摘要：
多任务学习（MTL）范式可以追溯到Caruana（1997）的早期论文，其中认为可以使用来自多个任务的数据，目的是获得比独立学习每个任务更好的性能。具有冲突目标的MTL的解决方案需要对它们之间的权衡进行建模，这通常超出了直接线性组合所能实现的范围。一个理论上有原则和计算上有效的策略是找到不被其他人支配的解决方案，因为它是在帕累托分析中解决的。在多任务学习环境中出现的多目标优化问题具有特定的特征，并且需要adhoc方法。这些功能的分析和一个新的计算方法的建议是这项工作的重点。多目标进化算法（MOEAs）可以很容易地包括优势的概念，因此帕累托分析。MOEA的主要缺点是函数评估的低样本效率。这个缺点的关键原因是，大多数的进化方法不使用模型来近似的目标函数。贝叶斯优化采用了一种完全不同的基于代理模型（如高斯过程）的方法。在这篇论文中，输入空间中的解被表示为概率分布，封装了函数求值中包含的知识。在这个概率分布的空间中，赋予Wasserstein距离给出的度量，可以设计一种新的算法MOEA/WST，其中模型不直接在目标函数上，而是在中间信息空间中，其中来自输入空间的对象被映射到直方图中。计算结果表明，MOEA/WST算法的样本效率和Pareto集的质量明显优于标准MOEA算法。
英文摘要：
The multi-task learning (MTL) paradigm can be traced back to an early paper of Caruana (1997) in which it was argued that data from multiple tasks can be used with the aim to obtain a better performance over learning each task independently. A solution of MTL with conflicting objectives requires modelling the trade-off among them which is generally beyond what a straight linear combination can achieve. A theoretically principled and computationally effective strategy is finding solutions which are not dominated by others as it is addressed in the Pareto analysis. Multi-objective optimization problems arising in the multi-task learning context have specific features and require adhoc methods. The analysis of these features and the proposal of a new computational approach represent the focus of this work. Multi-objective evolutionary algorithms (MOEAs) can easily include the concept of dominance and therefore the Pareto analysis. The major drawback of MOEAs is a low sample efficiency with respect to function evaluations. The key reason for this drawback is that most of the evolutionary approaches do not use models for approximating the objective function. Bayesian Optimization takes a radically different approach based on a surrogate model, such as a Gaussian Process. In this thesis the solutions in the Input Space are represented as probability distributions encapsulating the knowledge contained in the function evaluations. In this space of probability distributions, endowed with the metric given by the Wasserstein distance, a new algorithm MOEA/WST can be designed in which the model is not directly on the objective function but in an intermediate Information Space where the objects from the input space are mapped into histograms. Computational results show that the sample efficiency and the quality of the Pareto set provided by MOEA/WST are significantly better than in the standard MOEA.
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。
