PyFMTO


                       ____                __         
    ____     __  __   / __/  ____ ___     / /_   ____ 
   / __ \   / / / /  / /_   / __ `__ \   / __/  / __ \
  / /_/ /  / /_/ /  / __/  / / / / / /  / /_   / /_/ /
 / .___/   \__, /  /_/    /_/ /_/ /_/   \__/   \____/ 
/_/       /____/

PyFMTO is a pure Python library for federated many-task optimization research

<table align="center"> <tr> <td align="center"> <img src="https://github.com/Xiaoxu-Zhang/zxx-assets/raw/main/pyfmto-demo.gif" width="95%"/><br> Run experiments </td> <td align="center"> <img src="https://github.com/Xiaoxu-Zhang/zxx-assets/raw/main/pyfmto-iplot.gif" width="95%"/><br> Plot tasks </td> </tr> </table>

Usage

PyFMTO's CLI is available in any working directory, just make sure:

The Python environment is properly set up and activated
The PyFMTO is installed
A valid configuration file is provided in the current working directory

For more details, please refer to:

Quick Start
PyFMTO CLI
About fmto

Quick Start

Create an environment and install PyFMTO:

conda create -n fmto python=3.10
conda activate fmto
pip install pyfmto

Clone the fmto repository (why?):

git clone https://github.com/Xiaoxu-Zhang/fmto.git
cd fmto

Start the experiments:

pyfmto run

Generate reports:

pyfmto report

The reports will be saved in the folder out/results/<today>

Command-line Interface (CLI)

PyFMTO provides a command-line interface (CLI) for running experiments, analyzing results and get helps. The CLI layers are as follows:

pyfmto
   ├── -h/--help
   ├── run
   ├── report
   ├── list algorithms/problems/reports
   └── show algorithms.<alg_name>/problems.<prob_name>

Examples:

Get help:

pyfmto -h # or ↓
# pyfmto --help
# pyfmto list -h

Run experiments:

pyfmto run # or ↓
# pyfmto run -c config.yaml

Generate reports:

pyfmto report # or ↓
# pyfmto report -c config.yaml

List something:

pyfmto list algorithms  # or ↓ 
# pyfmto list problems

Show supported configurations:

pyfmto show algorithms.<alg_name>  # or ↓  
# pyfmto show problems.<prob_name>

Notes:

Every subcommand support -c/--config <config_file>

In the subcommands list and show, strings 'algorithms', 'problems', and 'reports' can be replaced with any prefix of length ≥ 1. PyFMTO matches the prefix to the corresponding category. For example:

pyfmto list algorithms is equivalent to:

pyfmto list a

pyfmto list al

pyfmto list alg

...

pyfmto show problems.<prob_name> is equivalent to:

pyfmto show p.<prob_name>

pyfmto show prob.<prob_name>

...

Use PyFMTO in Python


from pyfmto import Launcher, Reporter, ConfigLoader

if __name__ == '__main__':
    conf = ConfigLoader()
    launcher = Launcher(conf.launcher)
    reports = Reporter(conf.reporter)
    reports.to_excel()

Architecture and Ecosystem

Where the filled area represents the fully developed modules. And the non-filled area represents the base modules that can be inherited and extended.

The bottom layer listed the core technologies used in PyFMTO for computing, communicating, plotting and testing.

About fmto

The repository fmto is the official collection of published FMTO algorithms. The relationship between the fmto and PyFMTO is as follows:

The fmto is designed to provide a platform for researchers to compare and evaluate the performance of different FMTO algorithms. The repository is built on top of the PyFMTO library, which provides a flexible and extensible framework for implementing FMTO algorithms.

It also serves as a practical example of how to structure and perform experiments. The repository includes the following components:

A collection of published FMTO algorithms.
A config file (config.yaml) that provides guidance on how to set up and configure the experiments.
A template algorithm named "DEMO" that you can use as a basis for implementing your own algorithm.
A template problem named "demo" that you can use as a basis for implementing your own problem.

The config.yaml, algorithms/DEMO and problems/demo provided detailed instructions, you can even start your research without additional documentation. The fmto repository is currently in the early stages of development. I'm actively working on improving existing algorithms and adding new algorithms.

Algorithm's Components

An algorithm includes two parts: the client and the server. The client is responsible for optimizing the local problem and the server is responsible for aggregating the knowledge from the clients. The required components for client and server are as follows:

# myalg_client.py
from pyfmto import Client, Server

class MyClient(Client):
 def __init__(self, problem, **kwargs):
  super().__init__(problem)

 def optimize():
  # implement the optimizer
  pass

class MyServer(Server):
 def __init__(self, **kwargs):
  super().__init__():
 
 def aggregate(self) -> None:
  # implement the aggregate logic
  pass

 def handle_request(self, pkg) -> Any:
  # handle the requests of clients to exchange data
  pass

Problem's Components

There are two types of problems: single-task problems and multitask problems. A single-task problem is a problem that has only one objective function. A multitask problem is a problem that has multiple single-task problems. To define a multitask problem, you should implement several SingleTaskProblem and then define a MultiTaskProblem to aggregate them.

Note: There are some classical SingleTaskProblem defined in pyfmto.problems.benchmarks module. You can use them directly.

import numpy as np
from numpy import ndarray
from pyfmto.problem import SingleTaskProblem, MultiTaskProblem
from typing import Union


class MySTP(SingleTaskProblem):

    def __init__(self, dim=2, **kwargs):
        super().__init__(dim=dim, obj=1, lb=0, ub=1, **kwargs)

    def _eval_single(self, x: ndarray):
        pass


class MyMTP(MultiTaskProblem):
    is_realworld = False
    intro = "user defined MTP"
    notes = "a demo of user-defined MTP"
    references = ['ref1', 'ref2']

    def __init__(self, dim=10, **kwargs):
        super().__init__(dim, **kwargs)

    def _init_tasks(self, dim, **kwargs) -> list[SingleTaskProblem]:
        # Duplicate MySTP for 10 here as an example
        return [MySTP(dim=dim, **kwargs) for _ in range(10)]

Tools

load_problem

from pyfmto import load_problem

# init a problem with customized args
prob = load_problem('arxiv2017', dim=2, fe_init=20, fe_max=50, npd=5)

# problem instance can be print
print(prob)

Visualization

SingleTaskProblem Visualization

from pyfmto.problem.benchmarks import Ackley

task = Ackley()
task.plot_2d(f'visualize2D')
task.plot_3d(f'visualize3D')
task.iplot_3d()  # interactive plotting

MultiTaskProblem Visualization

The right side interactive plotting at the beginning is generated by the following code:

from pyfmto import load_problem

if __name__ == '__main__':
    prob = load_problem('arxiv2017', dim=2)
    prob.iplot_tasks_3d(tasks_id=[2, 5, 12, 18])

Contributing

See contributing for instructions on how to contribute to PyFMTO.

Bugs/Requests

Please send bug reports and feature requests through github issue tracker. PyFMTO is currently under development now, and it's open to any constructive suggestions.

License

Distributed under the terms of the Apache 2.0 license.

Acknowledgements

Foundations

This project is supported, in part, by the National Natural Science Foundation of China under Grant 62006143; the Natural Science Foundation of Shandong Province under Grants ZR2025MS1012 and ZR2020MF152. I would like to express our sincere gratitude to Smart Healthcare and Big Data Laboratory, Shandong Women's University, for providing research facilities and technical support.

Mentorship and Team Support

I would like to express my sincere gratitude to the **Computational Intelligence and Appli

Pyfmto

Install / Use

README