Repository for "Improving evidential deep learning via multi-task learning," published in AAAI2022

Overview

Improving evidential deep learning via multi task learning

It is a repository of AAAI2022 paper, “Improving evidential deep learning via multi-task learning”, by Dongpin Oh and Bonggun Shin.

This repository contains the code to reproduce the Multi-task evidential neural network (MT-ENet), which uses the Lipschitz MSE loss function as the additional loss function of the evidential regression network (ENet). The Lipschitz MSE loss function can improve the accuracy of the ENet while preserving its uncertainty estimation capability, by avoiding gradient conflict with the NLL loss function—the original loss function of the ENet.

drawing

Setup

Please refer to "requirements.txt" for requring packages of this repo.

pip install -r requirements.txt

Training the ENet with the Lipschitz-MSE loss: example

from mtevi.mtevi import EvidentialMarginalLikelihood, EvidenceRegularizer, modified_mse
...
net = EvidentialNetwork() ## Evidential regression network
nll_loss = EvidentialMarginalLikelihood() ## original loss, NLL loss
reg = EvidenceRegularizer() ## evidential regularizer
mmse_loss = modified_mse ## lipschitz MSE loss
...
for inputs, labels in dataloader:
	gamma, nu, alpha, beta = net(inputs)
	loss = nll_loss(gamma, nu, alpha, beta, labels)
	loss += reg(gamma, nu, alpha, beta, labels)
	loss += mmse_loss(gamma, nu, alpha, beta, labels)
	loss.backward()	

Quick start

  • Synthetic data experiment.
python synthetic_exp.py
  • UCI regression benchmark experiments.
python uci_exp_norm -p energy
  • Drug target affinity (DTA) regression task on KIBA and Davis datasets.
python train_evinet.py -o test --type davis -f 0 --evi # ENet
python train_evinet.py -o test --type davis -f 0  # MT-ENet
  • Gradient conflict experiment on the DTA benchmarks
python check_conflict.py --type davis -f 0 # Conflict between the Lipschitz MSE (proposed) and NLL loss. 
python check_conflict.py --type davis -f 0 --abl # Conflict between the simple MSE loss and NLL loss.

Characteristic of the Lipschitz MSE loss

drawing

  • The Lipschitz MSE loss function can support training the ENet to more accurately predicts target values.
  • It regularizes its gradient to prevent gradient conflict with the NLL loss--the original loss function--if the NLL loss increases predictive uncertainty of the ENet.
  • Please check our paper for details.
Owner
deargen
deargen
Code of U2Fusion: a unified unsupervised image fusion network for multiple image fusion tasks, including multi-modal, multi-exposure and multi-focus image fusion.

U2Fusion Code of U2Fusion: a unified unsupervised image fusion network for multiple image fusion tasks, including multi-modal (VIS-IR, medical), multi

Han Xu 129 Dec 11, 2022
A highly efficient, fast, powerful and light-weight anime downloader and streamer for your favorite anime.

AnimDL - Download & Stream Your Favorite Anime AnimDL is an incredibly powerful tool for downloading and streaming anime. Core features Abuses the dev

KR 759 Jan 08, 2023
Encode and decode text application

Text Encoder and Decoder Encode and decode text in many ways using this application! Encode in: ASCII85 Base85 Base64 Base32 Base16 Url MD5 Hash SHA-1

Alice 1 Feb 12, 2022
African language Speech Recognition - Speech-to-Text

Swahili-Speech-To-Text Table of Contents Swahili-Speech-To-Text Overview Scenario Approach Project Structure data: models: notebooks: scripts tests: l

2 Jan 05, 2023
This is a model to classify Vietnamese sign language using Motion history image (MHI) algorithm and CNN.

Vietnamese sign lagnuage recognition using MHI and CNN This is a model to classify Vietnamese sign language using Motion history image (MHI) algorithm

Phat Pham 3 Feb 24, 2022
A modular, research-friendly framework for high-performance and inference of sequence models at many scales

T5X T5X is a modular, composable, research-friendly framework for high-performance, configurable, self-service training, evaluation, and inference of

Google Research 1.1k Jan 08, 2023
The BCNet related data and inference model.

BCNet This repository includes the some source code and related dataset of paper BCNet: Learning Body and Cloth Shape from A Single Image, ECCV 2020,

81 Dec 12, 2022
FG-transformer-TTS Fine-grained style control in transformer-based text-to-speech synthesis

LST-TTS Official implementation for the paper Fine-grained style control in transformer-based text-to-speech synthesis. Submitted to ICASSP 2022. Audi

Li-Wei Chen 64 Dec 30, 2022
Code accompanying our paper Feature Learning in Infinite-Width Neural Networks

Empirical Experiments in "Feature Learning in Infinite-width Neural Networks" This repo contains code to replicate our experiments (Word2Vec, MAML) in

Edward Hu 37 Dec 14, 2022
PyTorch implementation of Neural Combinatorial Optimization with Reinforcement Learning.

neural-combinatorial-rl-pytorch PyTorch implementation of Neural Combinatorial Optimization with Reinforcement Learning. I have implemented the basic

Patrick E. 454 Jan 06, 2023
Created as part of CS50 AI's coursework. This AI makes use of knowledge entailment to calculate the best probabilities to win Minesweeper.

Minesweeper-AI Created as part of CS50 AI's coursework. This AI makes use of knowledge entailment to calculate the best probabilities to win Minesweep

Beckham 0 Jul 20, 2022
Implementation of Convolutional LSTM in PyTorch.

ConvLSTM_pytorch This file contains the implementation of Convolutional LSTM in PyTorch made by me and DavideA. We started from this implementation an

Andrea Palazzi 1.3k Dec 29, 2022
Code for "Localization with Sampling-Argmax", NeurIPS 2021

Localization with Sampling-Argmax [Paper] [arXiv] [Project Page] Localization with Sampling-Argmax Jiefeng Li, Tong Chen, Ruiqi Shi, Yujing Lou, Yong-

JeffLi 71 Dec 17, 2022
Efficient 3D human pose estimation in video using 2D keypoint trajectories

3D human pose estimation in video with temporal convolutions and semi-supervised training This is the implementation of the approach described in the

Meta Research 3.1k Dec 29, 2022
[ECCV 2020] Gradient-Induced Co-Saliency Detection

Gradient-Induced Co-Saliency Detection Zhao Zhang*, Wenda Jin*, Jun Xu, Ming-Ming Cheng ⭐ Project Home » The official repo of the ECCV 2020 paper Grad

Zhao Zhang 35 Nov 25, 2022
PyTorch Autoencoders - Implementing a Variational Autoencoder (VAE) Series in Pytorch.

PyTorch Autoencoders Implementing a Variational Autoencoder (VAE) Series in Pytorch. Inspired by this repository Model List check model paper conferen

Subin An 8 Nov 21, 2022
It's A ML based Web Site build with python and Django to find the breed of the dog

ML-Based-Dog-Breed-Identifier This is a Django Based Web Site To Identify the Breed of which your DOG belogs All You Need To Do is to Follow These Ste

Sanskar Dwivedi 2 Oct 12, 2022
[ICLR 2022] DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

DAB-DETR This is the official pytorch implementation of our ICLR 2022 paper DAB-DETR. Authors: Shilong Liu, Feng Li, Hao Zhang, Xiao Yang, Xianbiao Qi

336 Dec 25, 2022
A general framework for inferring CNNs efficiently. Reduce the inference latency of MobileNet-V3 by 1.3x on an iPhone XS Max without sacrificing accuracy.

GFNet-Pytorch (NeurIPS 2020) This repo contains the official code and pre-trained models for the glance and focus network (GFNet). Glance and Focus: a

Rainforest Wang 169 Oct 28, 2022