Learning where to learn - Gradient sparsity in meta and continual learning

Related tags

Deep Learning learning_where_to_learn
Overview

Learning where to learn - Gradient sparsity in meta and continual learning

In this paper, we investigate gradient sparsity found by MAML in various continual and few-shot learning scenarios.
Instead of only learning the initialization of neural network parameters, we additionally meta-learn parameters underneath a step function that stops gradient descent when smaller then 0.

We term this version Sparse-MAML - Link to the paper here.

Interestingly, we see that structured sparsity emerges in both the classic 4-layer ConvNet as well as a ResNet-12 for few-shot learning. This is accompanied by improved robustness and generalisation across many hyperparameters.

Note that Sparse-MAML is an extremely simple variant of MAML that possesses only the possibility to shut on/off training of specific parameters compared to proper gradient modulation.

This codebase implents the few-shot learning experiments that are presented in the paper. To reproduce the results in the paper, please follow these instructions:

Installation

#1. Install a conda env:

conda create -n sparse-MAML

#2. Activate the env:

source activate sparse-MAML

#3. Install anaconda:

conda install anaconda

#4. Install extra requiremetns (make sure you use the correct pip3):

pip3 install -r requirements.txt

#5. Run:

chmod u+x run_sparse_MAML.sh

#6. Execute:

./run_sparse_MAML.sh

Results

MiniImageNet Few-Shot MAML ANIL BOIL sparse-MAML sparse-ReLU-MAML
5-way 5-shot | ConvNet 63.15 61.50 66.45 67.03 64.84
5-way 1-shot | ConvNet 48.07 46.70 49.61 50.35 50.39
5-way 5-shot | ResNet12 69.36 70.03 70.50 70.02 73.01
5-way 1-shot | ResNet12 53.91 55.25 - 55.02 56.39

BOIL results are taken from the original paper.

This code based is heavily build on top of torchmeta.

You might also like...
Avalanche RL: an End-to-End Library for Continual Reinforcement Learning
Avalanche RL: an End-to-End Library for Continual Reinforcement Learning

Avalanche RL: an End-to-End Library for Continual Reinforcement Learning Avalanche Website | Getting Started | Examples | Tutorial | API Doc | Paper |

ContinualAI 43 Dec 24, 2022
Pytorch Implementation of Continual Learning With Filter Atom Swapping (ICLR'22 Spolight) Paper
Pytorch Implementation of Continual Learning With Filter Atom Swapping (ICLR'22 Spolight) Paper

Continual Learning With Filter Atom Swapping Pytorch Implementation of Continual Learning With Filter Atom Swapping (ICLR'22 Spolight) Paper If find t

null 11 Aug 29, 2022
Official Pytorch implementation of Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference (ICLR 2022)
Official Pytorch implementation of Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference (ICLR 2022)

The Official Implementation of CLIB (Continual Learning for i-Blurry) Online Continual Learning on Class Incremental Blurry Task Configuration with An

NAVER AI 34 Oct 26, 2022
CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation (ACMMM'21 Oral Paper)
CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation (ACMMM'21 Oral Paper)

CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation (ACMMM'21 Oral Paper) (Accepted for oral presentation at ACM

Minha Kim 1 Nov 12, 2021
ICSS - Interactive Continual Semantic Segmentation

Presentation This repository contains the code of our paper: Weakly-supervised c

Alteia 9 Jul 23, 2022
[CVPR 2022] CoTTA Code for our CVPR 2022 paper Continual Test-Time Domain Adaptation

CoTTA Code for our CVPR 2022 paper Continual Test-Time Domain Adaptation Prerequisite Please create and activate the following conda envrionment. To r

Qin Wang 87 Jan 8, 2023
Official repository for the paper
Official repository for the paper "Self-Supervised Models are Continual Learners" (CVPR 2022)

Self-Supervised Models are Continual Learners This is the official repository for the paper: Self-Supervised Models are Continual Learners Enrico Fini

Enrico Fini 73 Dec 18, 2022
[CVPR2022] Representation Compensation Networks for Continual Semantic Segmentation
[CVPR2022] Representation Compensation Networks for Continual Semantic Segmentation

RCIL [CVPR2022] Representation Compensation Networks for Continual Semantic Segmentation Chang-Bin Zhang1, Jia-Wen Xiao1, Xialei Liu1, Ying-Cong Chen2

Chang-Bin Zhang 71 Dec 28, 2022
H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.

H2O H2O is an in-memory platform for distributed, scalable machine learning. H2O uses familiar interfaces like R, Python, Scala, Java, JSON and the Fl

H2O.ai 6.1k Jan 5, 2023
Comments
  • Undefined variables and data pre-processing

    Undefined variables and data pre-processing

    Hi,

    Thanks for your nice work!!

    I have several questions.

    • Some variables are not defined before being used, e.g., class_augmentations in https://github.com/Johswald/learning_where_to_learn/blob/1441fec556a570a6bd688e0581352c830dba6f88/utils/utils.py#L120
    • How do U pre-process the data for each task? In other words, how do U get the data for each task in detail? Where could we find the related code?

    Best.

    opened by TiankaiHang 1
  • CVE-2007-4559 Patch

    CVE-2007-4559 Patch

    Patching CVE-2007-4559

    Hi, we are security researchers from the Advanced Research Center at Trellix. We have began a campaign to patch a widespread bug named CVE-2007-4559. CVE-2007-4559 is a 15 year old bug in the Python tarfile package. By using extract() or extractall() on a tarfile object without sanitizing input, a maliciously crafted .tar file could perform a directory path traversal attack. We found at least one unsantized extractall() in your codebase and are providing a patch for you via pull request. The patch essentially checks to see if all tarfile members will be extracted safely and throws an exception otherwise. We encourage you to use this patch or your own solution to secure against CVE-2007-4559. Further technical information about the vulnerability can be found in this blog.

    If you have further questions you may contact us through this projects lead researcher Kasimir Schulz.

    opened by TrellixVulnTeam 0
Owner
Johannes Oswald
Johannes Oswald
GitHub
Repository for "Exploring Sparsity in Image Super-Resolution for Efficient Inference", CVPR 2021

SMSR Reposity for "Exploring Sparsity in Image Super-Resolution for Efficient Inference" [arXiv] Highlights Locate and skip redundant computation in S

Longguang Wang 225 Dec 26, 2022
[Preprint] "Chasing Sparsity in Vision Transformers: An End-to-End Exploration" by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang

Chasing Sparsity in Vision Transformers: An End-to-End Exploration Codes for [Preprint] Chasing Sparsity in Vision Transformers: An End-to-End Explora

VITA 64 Dec 8, 2022
Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity

[ICLR 2022] Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity by Shiwei Liu, Tianlong Chen, Zahra Atashgahi, Xiaohan Chen, Ghada Sokar, Elena Mocanu, Mykola Pechenizkiy, Zhangyang Wang, Decebal Constantin Mocanu

VITA 18 Dec 31, 2022
Implementation of "Meta-rPPG: Remote Heart Rate Estimation Using a Transductive Meta-Learner"

Meta-rPPG: Remote Heart Rate Estimation Using a Transductive Meta-Learner This repository is the official implementation of Meta-rPPG: Remote Heart Ra

Eugene Lee 137 Dec 13, 2022
This project uses reinforcement learning on stock market and agent tries to learn trading. The goal is to check if the agent can learn to read tape. The project is dedicated to hero in life great Jesse Livermore.

Reinforcement-trading This project uses Reinforcement learning on stock market and agent tries to learn trading. The goal is to check if the agent can

Deepender Singla 1.4k Dec 22, 2022
Cl datasets - PyTorch image dataloaders and utility functions to load datasets for supervised continual learning

Continual learning datasets Introduction This repository contains PyTorch image

berjaoui 5 Aug 28, 2022
PyTorch implementation of: Michieli U. and Zanuttigh P., "Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations", CVPR 2021.

Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations This is the official PyTorch implementation

Multimedia Technology and Telecommunication Lab 42 Nov 9, 2022
Official code of CVPR 2021's PLOP: Learning without Forgetting for Continual Semantic Segmentation

PLOP: Learning without Forgetting for Continual Semantic Segmentation This repository contains all of our code. It is a modified version of Cermelli e

Arthur Douillard 116 Dec 14, 2022
CL-Gym: Full-Featured PyTorch Library for Continual Learning

CL-Gym: Full-Featured PyTorch Library for Continual Learning CL-Gym is a small yet very flexible library for continual learning research and developme

Iman Mirzadeh 36 Dec 25, 2022
PyTorch implementation of our Adam-NSCL algorithm from our CVPR2021 (oral) paper "Training Networks in Null Space for Continual Learning"

Adam-NSCL This is a PyTorch implementation of Adam-NSCL algorithm for continual learning from our CVPR2021 (oral) paper: Title: Training Networks in N

Shipeng Wang 34 Dec 21, 2022