Git Product home page Git Product logo

kdd19-iadm's Introduction

Code of KDD2019 Paper Adaptive Deep Models for Incremental Learning: Considering Capacity Scalability and Sustainability

Official implementation for KDD 2019 paper Adaptive Deep Models for Incremental Learning: Considering Capacity Scalability and Sustainability.

Requirement

  • python3.6.5
  • Pytorch0.4.1
  • numpy
  • scipy
  • sklearn

Files

--Incremental MNIST: Incremental MNIST dataset,including a training file and 4 testing files, which named as ldx_t.mat, lux_t.mat, rdx_t.mat and rux_t.mat.
--Draw.py: Draw the accuracy performance curve.
--Dataset.py: Prepare Incremental MNIST dataset.
--Test.py: Test performance of some model.
--IADM.py: A demo of our method.

Basic Usage

There are various parameters in the input structure paras:

--alp : Percentage of Fisher Information accumulated during Backpropagation.
--lr : Learning rate of our model
--drawstep: The frequence of Test duiring training (number of instance,default:12000)
--lamda : The regularization parameter in our paper.(In Eq(5).)

Quick Start

python IADM.py 

Parameters/options can be tuned to get better results.

Citation

Please cite our work if you feel the paper or the code are helpful.

@inproceedings{yang2019adaptive,
author = {Yang, Yang and Zhou, Da-Wei and Zhan, De-Chuan and Xiong, Hui and Jiang, Yuan},
title = {Adaptive Deep Models for Incremental Learning: Considering Capacity Scalability and Sustainability},
booktitle = {KDD},
address = {Anchorage, AK},
pages = {74--82},
year = {2019}
}

Contact

If there are any questions, please feel free to contact with the authors: Da-Wei Zhou ([email protected]) and Yang Yang ([email protected]). Enjoy the code.

kdd19-iadm's People

Contributors

zhoudw-zdw avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.