Codebase for the paper titled "Continual learning with local module selection"

Related tags

Deep LearningLMC
Overview

This repository contains the codebase for the paper Continual Learning via Local Module Composition.


Setting up the environemnt

Create a new conda environment and install the requirements.

conda create --name ENV python=3.7
conda activate ENV
pip install -r requirements.txt
pip install -e Utils/ctrl/
pip install Utils/nngeometry/

CTrL Benchmark

All experiments were run on Nvidia Quadro RTX 8000 GPUs. To run CTrL experiments use the following comands for different streams:

Stream S-

LMC (task agnostic)

python main_transfer.py --activate_after_str_oh=0 --momentum_bn 0.1 --track_running_stats_bn 1 --pr_name lmc_cr --shuffle_test 0 --init_oh=none --task_sequence s_minus --momentum_bn_decoder=0.1 --activation_structural=sigmoid --deviation_threshold=4 --depth=4 --epochs=100 --fix_layers_below_on_addition=0 --hidden_size=64 --lr=0.001 --mask_str_loss=1 --module_init=mean --multihead=gated_linear --normalize_oh=1 --optmize_structure_only_free_modules=1 --projection_layer_oh=0 --projection_phase_length=20 --reg_factor=10  --running_stats_steps=100 --str_prior_factor=1 --str_prior_temp=0.1 --structure_inv=ae --structure_inv_oh=linear_no_act --task_agnostic_test=1 --temp=0.1 --wdecay=0.001

(test acc. 0.6863, 15 modules)

MNTDP (task aware)

python main_transfer_mntdp.py --momentum_bn 0.1 --pr_name lmc_cr --copy_batchstats 1 --track_running_stats_bn 1 --task_sequence s_minus --gating MNTDP --shuffle_test 0 --epochs 100 --lr 1e-3 --wdecay 1e-3

(test acc. 0.667, 12 modules)

Stream S+

LMC

python main_transfer.py --activate_after_str_oh=0 --activation_structural=sigmoid --deviation_threshold=1.5 --early_stop_complete=0 --pr_name lmc_cr --epochs=100 --epochs_str_only_after_addition=1 --hidden_size=64 --init_oh=none --init_runingstats_on_addition=1 --keep_bn_in_eval_after_freeze=1 --lr=0.001 --module_init=most_likely --momentum_bn=0.1 --momentum_bn_decoder=0.1 --multihead=gated_linear --normalize_oh=1 --optmize_structure_only_free_modules=1 --projection_layer_oh=0 --projection_phase_length=5 --reg_factor=10 --running_stats_steps=100 --str_prior_factor=1 --str_prior_temp=0.1 --structure_inv=ae --structure_inv_oh=linear_no_act --task_agnostic_test=1 --task_sequence=s_plus --temp=1 --wdecay=0.001

(test acc. 0.6244, 22 modules)

MNTDP (task aware)

python main_transfer_mntdp.py --momentum_bn 0.1 --pr_name lmc_cr --copy_batchstats 1 --track_running_stats_bn 1 --task_sequence s_plus --gating MNTDP --shuffle_test 0 --epochs 100 --lr 1e-3 --wdecay 1e-3 --regenerate_seed 0

(test acc. 0.609, 18 modules)

Stream Sin

LMC

python main_transfer.py --activate_after_str_oh=0 --momentum_bn 0.1 --track_running_stats_bn 1 --pr_name lmc_cr --shuffle_test 0 --init_oh=none --task_sequence s_in --momentum_bn_decoder=0.1 --activation_structural=sigmoid --deviation_threshold=4 --depth=4 --epochs=100 --fix_layers_below_on_addition=0 --hidden_size=64 --lr=0.001 --mask_str_loss=1 --module_init=most_likely --multihead=gated_linear --normalize_oh=1 --optmize_structure_only_free_modules=1 --projection_layer_oh=0 --projection_phase_length=20 --reg_factor=10  --running_stats_steps=100 --str_prior_factor=1 --str_prior_temp=0.1 --structure_inv=ae --structure_inv_oh=linear_no_act --task_agnostic_test=1 --temp=0.1 --wdecay=0.001

(test acc. 0.7081, 21 modules)

MNTDP (task aware)

python main_transfer_mntdp.py --momentum_bn 0.1 --pr_name lmc_cr --copy_batchstats 1 --track_running_stats_bn 1 --task_sequence s_in --gating MNTDP --shuffle_test 0 --epochs 100 --lr 1e-3 --wdecay 1e-3 --regenerate_seed 0

(test acc. 0.6646, 15 modules)

Stream Sout

LMC

python main_transfer.py --activate_after_str_oh=0 --momentum_bn 0.1 --track_running_stats_bn 1 --pr_name lmc_cr --shuffle_test 0 --init_oh=none --task_sequence s_out --momentum_bn_decoder=0.1 --activation_structural=sigmoid --deviation_threshold=4 --depth=4 --epochs=100 --fix_layers_below_on_addition=0 --hidden_size=64 --lr=0.001 --mask_str_loss=1 --module_init=mean --multihead=gated_linear --normalize_oh=1 --optmize_structure_only_free_modules=1 --projection_layer_oh=0 --projection_phase_length=20 --reg_factor=10  --running_stats_steps=100 --str_prior_factor=1 --str_prior_temp=0.1 --structure_inv=ae --structure_inv_oh=linear_no_act --task_agnostic_test=1 --temp=0.1 --wdecay=0.001

(test acc. 0.5849, 15 modules)

MNTDP (task aware)

python main_transfer_mntdp.py --momentum_bn 0.1 --pr_name lmc_cr --copy_batchstats 1 --track_running_stats_bn 1 --task_sequence s_out --gating MNTDP --shuffle_test 0 --epochs 100 --lr 1e-3 --wdecay 0 --regenerate_seed 0

(test acc. 0.6567, 11 modules)

Stream Spl

LMC

python main_transfer.py --activate_after_str_oh=0 --activation_structural=sigmoid --pr_name lmc_cr --deviation_threshold=1.5 --early_stop_complete=0 --epochs=100 --hidden_size=64 --init_oh=none --init_runingstats_on_addition=0 --keep_bn_in_eval_after_freeze=1 --lr=0.001 --module_init=most_likely --momentum_bn=0.1 --momentum_bn_decoder=0.1 --multihead=gated_linear --normalize_oh=1 --optmize_structure_only_free_modules=1 --projection_layer_oh=0 --projection_phase_length=10 --reg_factor=10 --running_stats_steps=100 --str_prior_factor=1 --str_prior_temp=0.1 --structure_inv=ae --structure_inv_oh=linear_no_act --task_agnostic_test=1 --task_sequence=s_pl --temp=1 --regenerate_seed 0 --wdecay=0.001

(test acc. 0.6241, 19 modules)

MNTDP (task aware)

python main_transfer_mntdp.py --momentum_bn 0.1 --pr_name lmc_cr --copy_batchstats 1 --track_running_stats_bn 1 --task_sequence s_pl --gating MNTDP --shuffle_test 0 --epochs 100 --lr 1e-3 --wdecay 1e-4 --regenerate_seed 0

(test acc. 0.6391, 18 modules)


Stream Slong30 -- 30 tasks

LMC (task aware)

python main_transfer.py --activate_after_str_oh=0 --activation_structural=sigmoid --deviation_threshold=1.5 --epochs=50 --hidden_size=64 --init_oh=none --keep_bn_in_eval_after_freeze=1 --lr=0.001 --module_init=most_likely --momentum_bn_decoder=0.1 --multihead=gated_linear --n_tasks=100 --normalize_oh=1 --optmize_structure_only_free_modules=1 --projection_layer_oh=0 --projection_phase_length=5 --reg_factor=1 --running_stats_steps=50 --seed=180 --str_prior_factor=1 --str_prior_temp=0.01 --structure_inv=ae --structure_inv_oh=linear_no_act --task_agnostic_test=0 --task_sequence=s_long30 --temp=1 --wdecay=0.001

(test acc. 62.44, 50 modules)

MNTDP (task aware)

python main_transfer_mntdp.py --epochs=50 --hidden_size=64 --lr=0.001 --module_init=most_likely --multihead=gated_linear --n_tasks=100 --seed=180 --task_sequence=s_long30 --wdecay=0.001

(test acc. 64.58, 64 modules)


Stream Slong -- 100 tasks

LMC (task aware)

python main_transfer.py --activate_after_str_oh=0 --activation_structural=sigmoid --deviation_threshold=4 --epochs=100 --hidden_size=64 --init_oh=none --keep_bn_in_eval_after_freeze=1 --lr=0.001 --module_init=most_likely --momentum_bn_decoder=0.1 --multihead=gated_linear --n_tasks=100 --normalize_oh=1 --optmize_structure_only_free_modules=1 --projection_layer_oh=0 --projection_phase_length=5 --reg_factor=1 --running_stats_steps=50 --seed=180 --str_prior_factor=1 --str_prior_temp=0.01 --structure_inv=ae --structure_inv_oh=linear_no_act --task_agnostic_test=0 --task_sequence=s_long --temp=1 --pr_name s_long_cr --wdecay=0

(test acc. 63.88, 32 modules)

MNTDP (task aware)

python main_transfer_mntdp.py --momentum_bn 0.1 --n_tasks 100 --hidden_size 64 --searchspace topdown --keep_bn_in_eval_after_freeze 1 --pr_name s_long_cr --copy_batchstats 1 --track_running_stats_bn 1 --wand_notes correct_MNTDP --task_sequence s_long --gating MNTDP --shuffle_test 0 --epochs 50 --lr 1e-3 --wdecay 1e-3

(test acc. 68.92, 142 modules)


OOD generalization experiments

LMC

python main_transfer.py --regenerate_seed 0 --deviation_threshold=8 --epochs=50 --pr_name lmc_cr --hidden_size=64 --keep_bn_in_eval_after_freeze=0 --lr=0.001 --module_init=none --momentum_bn_decoder=0.1 --normalize_data=1 --optmize_structure_only_free_modules=0 --projection_phase_length=10 --no_projection_phase 0 --reg_factor=10 --running_stats_steps=1000 --str_prior_factor=1 --str_prior_temp=0.1 --structure_inv=linear_no_act --task_sequence=s_ood --temp=1 --wdecay=0 --task_agnostic_test=0

EWC

python main_transfer.py --epochs=50 --ewc=1000 --hidden_size=256 --keep_bn_in_eval_after_freeze=0 --lr=0.001 --module_init=none --pr_name lmc_cr --multihead=usual --normalize_data=1  --task_sequence=s_ood --use_structural=0 --wdecay=0 --projection_phase_length=0

MNTDP

python main_transfer_mntdp.py --epochs=50 --regenerate_seed 0 --hidden_size=64 --keep_bn_in_eval_after_freeze=0 --pr_name lmc_cr --lr=0.01 --module_init=none --multihead=usual --normalize_data=1 --task_sequence=s_ood --use_structural=0 --wdecay=0

LMC (no projetion)

python main_transfer.py --regenerate_seed 0 --deviation_threshold=8 --epochs=50 --pr_name lmc_cr --hidden_size=64 --keep_bn_in_eval_after_freeze=0 --lr=0.001 --module_init=none --momentum_bn_decoder=0.1 --normalize_data=1 --optmize_structure_only_free_modules=0 --projection_phase_length=0 --no_projection_phase 1 --reg_factor=10 --running_stats_steps=1000 --str_prior_factor=1 --str_prior_temp=0.1 --structure_inv=linear_no_act --task_sequence=s_ood --temp=1 --wdecay=0

Plug and play (combining independently trained modular learners)

python main_plug_and_play.py --activate_after_str_oh=0 --activation_structural=sigmoid --deviation_threshold=1.5 --early_stop_complete=0 --epochs=100 --epochs_str_only_after_addition=1 --pr_name lmc_cr --hidden_size=64 --init_oh=none --init_runingstats_on_addition=1 --keep_bn_in_eval_after_freeze=1 --lr=0.001 --module_init=mean --momentum_bn=0.1 --momentum_bn_decoder=0.1 --multihead=gated_linear --n_tasks=3 --normalize_oh=1 --optmize_structure_only_free_modules=1 --projection_layer_oh=0 --projection_phase_length=5 --reg_factor=10 --running_stats_steps=10 --str_prior_factor=1 --str_prior_temp=0.1 --structure_inv=ae --structure_inv_oh=linear_no_act --task_agnostic_test=1 --task_sequence=s_pnp_comp --temp=1 --wdecay=0.001

A list of hyperparameters used for other baselines can be found in the baselines.txt file.


References

Owner
Oleksiy Ostapenko
Oleksiy Ostapenko
Welcome to The Eigensolver Quantum School, a quantum computing crash course designed by students for students.

TEQS Welcome to The Eigensolver Quantum School, a crash course designed by students for students. The aim of this program is to take someone who has n

The Eigensolvers 53 May 18, 2022
Code for our paper at ECCV 2020: Post-Training Piecewise Linear Quantization for Deep Neural Networks

PWLQ Updates 2020/07/16 - We are working on getting permission from our institution to release our source code. We will release it once we are granted

54 Dec 15, 2022
Milano is a tool for automating hyper-parameters search for your models on a backend of your choice.

Milano (This is a research project, not an official NVIDIA product.) Documentation https://nvidia.github.io/Milano Milano (Machine learning autotuner

NVIDIA Corporation 147 Dec 17, 2022
ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis

ImageBART NeurIPS 2021 Patrick Esser*, Robin Rombach*, Andreas Blattmann*, Björn Ommer * equal contribution arXiv | BibTeX | Poster Requirements A sui

CompVis Heidelberg 110 Jan 01, 2023
Tensorflow implementation and notebooks for Implicit Maximum Likelihood Estimation

tf-imle Tensorflow 2 and PyTorch implementation and Jupyter notebooks for Implicit Maximum Likelihood Estimation (I-MLE) proposed in the NeurIPS 2021

NEC Laboratories Europe 69 Dec 13, 2022
Towards Debiasing NLU Models from Unknown Biases

Towards Debiasing NLU Models from Unknown Biases Abstract: NLU models often exploit biased features to achieve high dataset-specific performance witho

Ubiquitous Knowledge Processing Lab 22 Jun 14, 2022
TensorFlow Tutorials with YouTube Videos

TensorFlow Tutorials Original repository on GitHub Original author is Magnus Erik Hvass Pedersen Introduction These tutorials are intended for beginne

9.1k Jan 02, 2023
The most simple and minimalistic navigation dashboard.

Navigation This project follows a goal to have simple and lightweight dashboard with different links. I use it to have my own self-hosted service dash

Yaroslav 23 Dec 23, 2022
Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021

LoFTR: Detector-Free Local Feature Matching with Transformers Project Page | Paper LoFTR: Detector-Free Local Feature Matching with Transformers Jiami

ZJU3DV 1.4k Jan 04, 2023
Calling Julia from Python - an experiment on data loading

Calling Julia from Python - an experiment on data loading See the slides. TLDR After reading Patrick's blog post, we decided to try to replace C++ wit

Abel Siqueira 8 Jun 07, 2022
(CVPR 2022 - oral) Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry

Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry Official implementation of the paper Multi-View Depth Est

Bae, Gwangbin 138 Dec 28, 2022
Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

Semantic Segmentation on MIT ADE20K dataset in PyTorch This is a PyTorch implementation of semantic segmentation models on MIT ADE20K scene parsing da

MIT CSAIL Computer Vision 4.5k Jan 08, 2023
A Free and Open Source Python Library for Multiobjective Optimization

Platypus What is Platypus? Platypus is a framework for evolutionary computing in Python with a focus on multiobjective evolutionary algorithms (MOEAs)

Project Platypus 424 Dec 18, 2022
The official code repository for examples in the O'Reilly book 'Generative Deep Learning'

Generative Deep Learning Teaching Machines to paint, write, compose and play The official code repository for examples in the O'Reilly book 'Generativ

David Foster 1.3k Dec 29, 2022
A Dying Light 2 (DL2) PAKFile Utility for Modders and Mod Makers.

Dying Light 2 PAKFile Utility A Dying Light 2 (DL2) PAKFile Utility for Modders and Mod Makers. This tool aims to make PAKFile (.pak files) modding a

RHQ Online 12 Aug 26, 2022
A Simplied Framework of GAN Inversion

Framework of GAN Inversion Introcuction You can implement your own inversion idea using our repo. We offer a full range of tuning settings (in hparams

Kangneng Zhou 13 Sep 27, 2022
Learning where to learn - Gradient sparsity in meta and continual learning

Learning where to learn - Gradient sparsity in meta and continual learning In this paper, we investigate gradient sparsity found by MAML in various co

Johannes Oswald 28 Dec 09, 2022
This repo contains the code for the paper "Efficient hierarchical Bayesian inference for spatio-temporal regression models in neuroimaging" that has been accepted to NeurIPS 2021.

Dugh-NeurIPS-2021 This repo contains the code for the paper "Efficient hierarchical Bayesian inference for spatio-temporal regression models in neuroi

Ali Hashemi 5 Jul 12, 2022
This repository gives an example on how to preprocess the data of the HECKTOR challenge

HECKTOR 2021 challenge This repository gives an example on how to preprocess the data of the HECKTOR challenge. Any other preprocessing is welcomed an

56 Dec 01, 2022
TensorFlow implementation for Bayesian Modeling and Uncertainty Quantification for Learning to Optimize: What, Why, and How

Bayesian Modeling and Uncertainty Quantification for Learning to Optimize: What, Why, and How TensorFlow implementation for Bayesian Modeling and Unce

Shen Lab at Texas A&M University 8 Sep 02, 2022