Multi-Objective Evolutionary Federated Learning

Federated Multi-Task Learning

Federated learning poses new statistical and systems challenges in training machinelearning models over distributed networks of devices. In this work, we show thatmulti-task learning is naturally suited to handle the statistical challenges of thissetting, and propose a novel systems-aware optimization method, MOCHA, that isrobust to practical systems issues. Our method and theor...

Multi-Objective Evolutionary Algorithms

Evolutionary Multi-Objective Algorithms

The versatility that genetic algorithm (GA) has proved to have for solving different problems, has make it the first choice of researchers to deal with new challenges. Currently, GAs are the most well known evolutionary algorithms, because their intuitive principle of operation and their relatively simple implementation; besides they have the ability to reflect the philosophy of evolutionary co...

Multi-Objective Evolutionary Algorithms

Real world optimization problems are often too complex to be solved through analytical means. Evolutionary algorithms, a class of algorithms that borrow paradigms from nature, are particularly well suited to address such problems. These algorithms are stochastic methods of optimization that have become immensely popular recently, because they are derivative-free methods, are not as prone to get...

An Evolutionary Multi-objective Discretization based on Normalized Cut

Learning models and related results depend on the quality of the input data. If raw data is not properly cleaned and structured, the results are tending to be incorrect. Therefore, discretization as one of the preprocessing techniques plays an important role in learning processes. The most important challenge in the discretization process is to reduce the number of features’ values. This operat...