Graph-based machine learning for chemical property prediction
-
Updated
Jul 25, 2024 - Python
Graph-based machine learning for chemical property prediction
1. Use BERT, ALBERT and GPT2 as tensorflow2.0's layer. 2. Implement GCN, GAN, GIN and GraphSAGE based on message passing.
Feature Expansion for Graph Neural Networks [ICML-2023]
Concurrent, Asynchronous, Distributed, Communicating Tasks with Python
High-Level Property Specification Language
Erlang node implemented in Python 3.5+ (Asyncio-based)
[ICML 2023] Official code for our paper: 'Conditional Tree Matching for Inference-Time Adaptation of Tree Prediction Models'
Package for generating and inverse-designing 2D lattice materials. Represents lattices as heterogeneous graphs and utilizes message passing, automatic differentiation and surrogate gradients for the inverse design.
COntagion Simulation And Source Identification: a Python package for graph diffusion source inference
Gradient gating (ICLR 2023)
Official Implementation of Multi-Masked Aggregators for Graph Neural Networks in Pytorch and PyTorch Geometric
Refactored the Udaconnect app (from monolithic to microservices) and implemented Kafka, gRPC, and RESTful API to allow message passing between the microservices. I also created OpenAPI documentation for the API endpoints and provided a Postman library for the endpoints created.
This is one of my projects under Udacity's Cloud Native Application Architecture Nanodegree. In this project, I have refactored Udaconnect's monolithic architecture into a microservice architecture using several message passing techniques.
Implementation for ReFactor GNNs
The official PyTorch implementation of "Pathfinder Discovery Networks for Neural Message Passing" (WebConf '21)
Example of High-Speed Subscriber Patterns in ZeroMQ
Advanced Message Passing
DGL implementation of GNN-CCA: Graph Neural Networks for Cross-Camera Data Association [arXiv:2201.06311]
Linear Gaussian Bayesian Networks - Inference, Parameter Learning and Representation. 🖧
Belief propagation with sparse matrices (scipy.sparse) in Python for LDPC codes. Includes NumPy implementation of message passing (min-sum and sum-product) and a few other decoders.
Add a description, image, and links to the message-passing topic page so that developers can more easily learn about it.
To associate your repository with the message-passing topic, visit your repo's landing page and select "manage topics."