tandychao Goto Github PK

ml-1m

New algorithms for Large-scale Collaborative Ranking: PrimalCR and PrimalCR++

mltuner-geeps

GeePS with automatic tuning on learning rate, momentum, batch size, data staleness and more.

models

Models built with TensorFlow

models-1

mrec

A recommender systems development and evaluation package by Mendeley

mtlearn

Code release for "Learning Multiple Tasks with Multilinear Relationship Networks" (NIPS 2017)

mujoco-py

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

multiagent-particle-envs

multirunner

This is a python package for multi-process running.

multitask-learn

multitaskvision

Code for 'Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics'

muzero-general

MuZero

muzero-pytorch

Pytorch Implementation of MuZero

ndcg

neuir-weak-supervision

Code for Content-Based Weak Supervision for Ad-Hoc Re-Ranking, accepted at SIGIR 2019.

neural-attentive-item-similarity-model

TensorFlow Implementation of Neural Attentive Item Similarity Model for Recommendation

neural-em

Code for the "Neural Expectation Maximization" paper.

neural-net-matrix-factorization

Exploring neural networks for collaborative filtering.

neural_collaborative_filtering

neural_factorization_machine

nextitnet

A Simple Convolutional Generative Network for Next Item Recommendation

niapg

Matlab Code for "Efficient Inexact Proximal Gradient Algorithm for Nonconvex Problems" IJCAI 2017

nn_playground

Experimental implementation of novel neural network structures

nncf

Code for paper "On Sampling Strategies for Neural Network-based Collaborative Filtering"

node2vec

nrlpapers

Must-read papers on network representation learning (NRL)/network embedding (NE)

onlinemaxnorm-nips2014

Matlab code for NIPS 2014 work "Online Optimization for Max-Norm Regularization"

open_spiel

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

openlearning4deeprecsys

Some deep learning based recsys for open learning.

optimal-rtb

A benchmarking framework supporting the experiments in KDD'14 paper "Optimal Real-Time Bidding for Display Advertising"