{"id":15949363,"url":"https://github.com/mfreidank/federated_learning_workshop_amld2021","last_synced_at":"2026-04-27T01:31:25.051Z","repository":{"id":46761190,"uuid":"302771588","full_name":"MFreidank/Federated_Learning_Workshop_AMLD2021","owner":"MFreidank","description":null,"archived":false,"fork":false,"pushed_at":"2021-09-28T19:47:19.000Z","size":4681,"stargazers_count":1,"open_issues_count":1,"forks_count":2,"subscribers_count":3,"default_branch":"main","last_synced_at":"2026-01-02T07:02:38.890Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/MFreidank.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-10-09T23:09:46.000Z","updated_at":"2021-09-28T19:47:22.000Z","dependencies_parsed_at":"2022-09-18T04:40:48.126Z","dependency_job_id":null,"html_url":"https://github.com/MFreidank/Federated_Learning_Workshop_AMLD2021","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/MFreidank/Federated_Learning_Workshop_AMLD2021","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MFreidank%2FFederated_Learning_Workshop_AMLD2021","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MFreidank%2FFederated_Learning_Workshop_AMLD2021/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MFreidank%2FFederated_Learning_Workshop_AMLD2021/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MFreidank%2FFederated_Learning_Workshop_AMLD2021/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MFreidank","download_url":"https://codeload.github.com/MFreidank/Federated_Learning_Workshop_AMLD2021/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MFreidank%2FFederated_Learning_Workshop_AMLD2021/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32319559,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-26T23:26:28.701Z","status":"ssl_error","status_checked_at":"2026-04-26T23:26:25.802Z","response_time":129,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-10-07T12:14:02.561Z","updated_at":"2026-04-27T01:31:25.036Z","avatar_url":"https://github.com/MFreidank.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Federated Learning Workshop AMLD2021\n\n## Preparations\n\nWe've tried to keep this workshop light on the setup/preparations side by using \n[Google Colab](https://colab.research.google.com/) for a majority of the materials and exercises that we will cover. \n\nTherefore, the main requirement is access to a Google account which would be required \nto access the notebooks we prepared. \n\nPlease ensure you have access to a google account you can use, or [create one](https://accounts.google.com/SignUp?hl=en)\nin preparation for the session. \n\nDon't worry about studying the notebooks below, these will be covered as \nintegral part of the workshop and will remain available to you afterwards as well.\n\n\n## 1. Interactive Examples: torch Federated Learning\n### 1.1 Simulating Federated Learning using torch\n\nThis example introduces basic components that are part of the Federated Learning workflow.\nIn the simulation we:\n1. Train a baseline model on the CIFAR10 dataset.\n2. Simulate a server \u0026 client and send a model from server to client to be trained.\n3. Simulate a server \u0026 multiple clients and train a global model on multiple clients and perform FedAvg.\n\nPlease use the google colab notebook link below to access the relevant material:\n\n[PyTorch FL Simulation Notebook](https://colab.research.google.com/drive/1a1Ekw5jFs8eYOxAhsBRwFAt3WxEBsyf9)\n\n## 2. Interactive Examples: Syft\n\n### 2.1 Simple Syft Duet Intro\n\nThis example introduces basic primitives of a successful PySyft Duet Exchange: \n* establishing a duet connection between data owner and client\n* safely providing information about available datasets as a data owner\n* issuing access requests as a client/data scientist\n* approving/denying requests for data access as a data owner\n\nPlease use the google colab notebook links below to access the relevant materials:\n\n* Data Owner:\n[Data Owner Notebook](https://colab.research.google.com/drive/1lPa95bboyd_4GTljn_PJtAgxra3l7T7e?usp=sharing)\n\n* Data Scientist:\n[Data Scientist Notebook](https://colab.research.google.com/drive/107zodT2X6rogAoYQSUprOQu-mkk7BPs3?usp=sharing)\n\n### 2.2 Syft FL Example\n\nThis example showcases a basic federated learning exchange (with a data scientist modeling against \ndata held by two separate data owners) using PySyft Duet. \n\nPlease use the google colab notebook links below to access the relevant materials:\n\n* Data Owner 1:\n[Data Owner 1 Notebook](https://colab.research.google.com/drive/12pEcshA3eH55LeAWO_dmg5EflDQWpTlD?usp=sharing)\n\n* Data Owner 2:\n[Data Owner 2 Notebook](https://colab.research.google.com/drive/1c_O_4TfkKT2jKl5EtYKnxAwISEBefXzK?usp=sharing)\n\n* Data Scientist:\n[Data Scientist Notebook](https://colab.research.google.com/drive/1o8wOkrprb8ecKkkiU9AdL2NHxZwA6g4F?usp=sharing)\n\n### 2.3 Opacus Example\nThis example discusses how to use opacus for differential privacy to ensure\ndata privacy while training models collaboratively.\n\nPlease use the google colab notebook link below to access the relevant material:\n\n* Opacus Example:\n[Opacus Example Notebook](https://colab.research.google.com/drive/1bWfrmQ4FuJ0UxyU0lkPNdH384iI9JDWm?usp=sharing)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmfreidank%2Ffederated_learning_workshop_amld2021","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmfreidank%2Ffederated_learning_workshop_amld2021","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmfreidank%2Ffederated_learning_workshop_amld2021/lists"}