Timezone: »
We present FedSparsify, a sparsification strategy for federated training based on progressive weight magnitude pruning, which provides several benefits. First, since the size of the network becomes increasingly smaller, computation and communication costs during training are reduced. Second, the models are incrementally constrained to a smaller set of parameters, which facilitates alignment/merging of the local models, and results in improved learning performance at high sparsity. Third, the final sparsified model is significantly smaller, which improves inference efficiency. We analyze FedSparsify's convergence and empirically demonstrate that FedSparsify can learn a subnetwork smaller than a tenth of the size of the original model with the same or better accuracy compared to existing pruning and no-pruning baselines across several challenging federated learning environments. Our approach leads to an average 4-fold inference efficiency speedup and a 15-fold model size reduction over different domains and neural network architectures.
Author Information
Dimitris Stripelis (Information Sciences Institute, USC)
Dimitris Stripelis is currently a Ph.D. candidate in Computer Science at the University of Southern California (USC) graduating this Spring (2023) and his thesis is on Federated Machine Learning Systems for Heterogeneous Environments. Dimitris holds a BSc in Computer Science from the Athens University of Economics and Business and an MSc in Computer Science (Data Science specialization) from the University of Southern California.
Umang Gupta (University of Southern California)
Greg Ver Steeg (USC Information Sciences Institute)
Jose-Luis Ambite (University of Southern California)
More from the Same Authors
-
2022 : Bounding the Effects of Continuous Treatments for Hidden Confounders »
Myrl Marmarelis · Greg Ver Steeg · Neda Jahanshad · Aram Galstyan -
2021 Poster: Information-theoretic generalization bounds for black-box learning algorithms »
Hrayr Harutyunyan · Maxim Raginsky · Greg Ver Steeg · Aram Galstyan -
2021 Poster: Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling »
Greg Ver Steeg · Aram Galstyan -
2021 Poster: Implicit SVD for Graph Representation Learning »
Sami Abu-El-Haija · Hesham Mostafa · Marcel Nassar · Valentino Crespi · Greg Ver Steeg · Aram Galstyan -
2020 Workshop: Deep Learning through Information Geometry »
Pratik Chaudhari · Alexander Alemi · Varun Jog · Dhagash Mehta · Frank Nielsen · Stefano Soatto · Greg Ver Steeg -
2019 : Poster Session »
Gergely Flamich · Shashanka Ubaru · Charles Zheng · Josip Djolonga · Kristoffer Wickstrøm · Diego Granziol · Konstantinos Pitas · Jun Li · Robert Williamson · Sangwoong Yoon · Kwot Sin Lee · Julian Zilly · Linda Petrini · Ian Fischer · Zhe Dong · Alexander Alemi · Bao-Ngoc Nguyen · Rob Brekelmans · Tailin Wu · Aditya Mahajan · Alexander Li · Kirankumar Shiragur · Yair Carmon · Linara Adilova · SHIYU LIU · Bang An · Sanjeeb Dash · Oktay Gunluk · Arya Mazumdar · Mehul Motani · Julia Rosenzweig · Michael Kamp · Marton Havasi · Leighton P Barnes · Zhengqing Zhou · Yi Hao · Dylan Foster · Yuval Benjamini · Nati Srebro · Michael Tschannen · Paul Rubenstein · Sylvain Gelly · John Duchi · Aaron Sidford · Robin Ru · Stefan Zohren · Murtaza Dalal · Michael A Osborne · Stephen J Roberts · Moses Charikar · Jayakumar Subramanian · Xiaodi Fan · Max Schwarzer · Nicholas Roberts · Simon Lacoste-Julien · Vinay Prabhu · Aram Galstyan · Greg Ver Steeg · Lalitha Sankar · Yung-Kyun Noh · Gautam Dasarathy · Frank Park · Ngai-Man (Man) Cheung · Ngoc-Trung Tran · Linxiao Yang · Ben Poole · Andrea Censi · Tristan Sylvain · R Devon Hjelm · Bangjie Liu · Jose Gallego-Posada · Tyler Sypherd · Kai Yang · Jan Nikolas Morshuis -
2019 Poster: Fast structure learning with modular regularization »
Greg Ver Steeg · Hrayr Harutyunyan · Daniel Moyer · Aram Galstyan -
2019 Spotlight: Fast structure learning with modular regularization »
Greg Ver Steeg · Hrayr Harutyunyan · Daniel Moyer · Aram Galstyan -
2019 Poster: Exact Rate-Distortion in Autoencoders via Echo Noise »
Rob Brekelmans · Daniel Moyer · Aram Galstyan · Greg Ver Steeg -
2018 Poster: Invariant Representations without Adversarial Training »
Daniel Moyer · Shuyang Gao · Rob Brekelmans · Aram Galstyan · Greg Ver Steeg -
2017 : Coffee break and Poster Session II »
Mohamed Kane · Albert Haque · Vagelis Papalexakis · John Guibas · Peter Li · Carlos Arias · Eric Nalisnick · Padhraic Smyth · Frank Rudzicz · Xia Zhu · Theodore Willke · Noemie Elhadad · Hans Raffauf · Harini Suresh · Paroma Varma · Yisong Yue · Ognjen (Oggi) Rudovic · Luca Foschini · Syed Rameel Ahmad · Hasham ul Haq · Valerio Maggio · Giuseppe Jurman · Sonali Parbhoo · Pouya Bashivan · Jyoti Islam · Mirco Musolesi · Chris Wu · Alexander Ratner · Jared Dunnmon · Cristóbal Esteban · Aram Galstyan · Greg Ver Steeg · Hrant Khachatrian · Marc Górriz · Mihaela van der Schaar · Anton Nemchenko · Manasi Patwardhan · Tanay Tandon -
2016 Poster: Variational Information Maximization for Feature Selection »
Shuyang Gao · Greg Ver Steeg · Aram Galstyan -
2014 Poster: Discovering Structure in High-Dimensional Data Through Correlation Explanation »
Greg Ver Steeg · Aram Galstyan