GyroSPD: Vector-valued Distance and Gyrocalculus on the Space of Symmetric Positive Definite Matrices

Related tags

Deep Learninggyrospd
Overview

GyroSPD

Code for the paper "Vector-valued Distance and Gyrocalculus on the Space of Symmetric Positive Definite Matrices" accepted at NeurIPS 2021.

Requirements

  • Python == 3.7
  • Pytorch == 1.5.1: conda install pytorch==1.5.1 torchvision==0.6.1 [cpuonly | cudatoolkit=10.2] -c pytorch.
  • Geoopt == 0.3.1: install from repository is advised
  • tensorboardx
  • tqdm

Running experiments

0. Init repo

sh init.sh

It will uncompress the Knowledge graphs and create the necessary folders. Datasets are taken from https://github.com/villmow/datasets_knowledge_embedding

1. Preprocess Dataset

python preprocess.py

This will preprocess all folders inside the data folder. It looks for "train", "valid", "test" files in tsv format with triples of "head relation tail"

2. Run Experiments

python -m torch.distributed.launch --nproc_per_node=N_CPUS --master_port=2055 train.py \\
            --n_procs=N_CPUS \\
            --data=PREP \\
            --run_id=RUN_ID \\
            --results_file=out/results.csv \\
            --model=MODEL \\
            --metric=riem \\
            --dims=10 \\
            --learning_rate=1e-4 \\
            --val_every=25 \\
            --patience=50 \\
            --batch_size=2048 \\
            --epochs=1000 \\
            --train_bias

Experiments can be run distributed over multiple CPUs/GPUs with N_CPUS. PREP must be the name of the folder inside data. Results will be reported in results_file with run_id as the name. For model and metric see Models and Metrics

Models and Metrics

The parameter --model can be set with:

  • tgspd: Applies a scaling on the head embedding
  • tgrotspd: Applies a rotation on the head embedding
  • tgrefspd: Applies a reflection on the head embedding
  • tgattnspd: Combines rotation and reflection with an attention mechanism

The parameter --metric can be set with:

  • riem: Riemannian metric
  • fone: Finsler One
  • finf: Finsler Infinity

TODO

  • Migrate to latest pytorch
  • Remove geoopt dependency / Migrate to latest geoopt

Citation

The source code and data in this repository aims at facilitating the study of graph embeddings in the space of symmetric positive definite matrices. If you use the code/data, please cite it as follows:

TBD
Owner
Federico Lopez
PhD Student on NLP at HITS
Federico Lopez
HiFT: Hierarchical Feature Transformer for Aerial Tracking (ICCV2021)

HiFT: Hierarchical Feature Transformer for Aerial Tracking Ziang Cao, Changhong Fu, Junjie Ye, Bowen Li, and Yiming Li Our paper is Accepted by ICCV 2

Intelligent Vision for Robotics in Complex Environment 55 Nov 23, 2022
This is the official PyTorch implementation for "Mesa: A Memory-saving Training Framework for Transformers".

A Memory-saving Training Framework for Transformers This is the official PyTorch implementation for Mesa: A Memory-saving Training Framework for Trans

Zhuang AI Group 105 Dec 06, 2022
Matthew Colbrook 1 Apr 08, 2022
Research Artifact of USENIX Security 2022 Paper: Automated Side Channel Analysis of Media Software with Manifold Learning

Automated Side Channel Analysis of Media Software with Manifold Learning Official implementation of USENIX Security 2022 paper: Automated Side Channel

Yuanyuan Yuan 175 Jan 07, 2023
Walk with fastai

Shield: This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Walk with fastai What is this p

Walk with fastai 124 Dec 10, 2022
Multitask Learning Strengthens Adversarial Robustness

Multitask Learning Strengthens Adversarial Robustness

Columbia University 15 Jun 10, 2022
Easy-to-use library to boost AI inference leveraging state-of-the-art optimization techniques.

NEW RELEASE How Nebullvm Works • Tutorials • Benchmarks • Installation • Get Started • Optimization Examples Discord | Website | LinkedIn | Twitter Ne

Nebuly 1.7k Dec 31, 2022
Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation (CVPR 2022)

CCAM (Unsupervised) Code repository for our paper "CCAM: Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localizati

Computer Vision Insitute, SZU 113 Dec 27, 2022
Consensus Learning from Heterogeneous Objectives for One-Class Collaborative Filtering

Consensus Learning from Heterogeneous Objectives for One-Class Collaborative Filtering This repository provides the source code of "Consensus Learning

SeongKu-Kang 6 Apr 29, 2022
This repository is to support contributions for tools for the Project CodeNet dataset hosted in DAX

The goal of Project CodeNet is to provide the AI-for-Code research community with a large scale, diverse, and high quality curated dataset to drive innovation in AI techniques.

International Business Machines 1.2k Jan 04, 2023
Out-of-Distribution Generalization of Chest X-ray Using Risk Extrapolation

OoD_Gen-Chest_Xray Out-of-Distribution Generalization of Chest X-ray Using Risk Extrapolation Requirements (Installations) Install the following libra

Enoch Tetteh 2 Oct 01, 2022
Shōgun

The SHOGUN machine learning toolbox Unified and efficient Machine Learning since 1999. Latest release: Cite Shogun: Develop branch build status: Donat

Shōgun ML 2.9k Jan 04, 2023
This is the implementation of GGHL (A General Gaussian Heatmap Labeling for Arbitrary-Oriented Object Detection)

GGHL: A General Gaussian Heatmap Labeling for Arbitrary-Oriented Object Detection This is the implementation of GGHL 👋 👋 👋 [Arxiv] [Google Drive][B

551 Dec 31, 2022
3D ResNet Video Classification accelerated by TensorRT

Activity Recognition TensorRT Perform video classification using 3D ResNets trained on Kinetics-400 dataset and accelerated with TensorRT P.S Click on

Akash James 39 Nov 21, 2022
Deploy pytorch classification model using Flask and Streamlit

Deploy pytorch classification model using Flask and Streamlit

Ben Seo 1 Nov 17, 2021
Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks

Introduction This repository contains the modified caffe library and network architectures for our paper "Automated Melanoma Recognition in Dermoscopy

Lequan Yu 47 Nov 24, 2022
LocUNet is a deep learning method to localize a UE based solely on the reported signal strengths from a set of BSs.

LocUNet LocUNet is a deep learning method to localize a UE based solely on the reported signal strengths from a set of BSs. The method utilizes accura

4 Oct 05, 2022
Toolkit for collecting and applying prompts

PromptSource Promptsource is a toolkit for collecting and applying prompts to NLP datasets. Promptsource uses a simple templating language to programa

BigScience Workshop 998 Jan 03, 2023
PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

Thalles Silva 1.7k Dec 28, 2022
PyTorch implementation of ENet

PyTorch-ENet PyTorch (v1.1.0) implementation of ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation, ported from the lua-torc

David Silva 333 Dec 29, 2022