DAIR Lab

DAIR Lab's repositories

open-box

Generalized and Efficient Blackbox Optimization System

Language:PythonNOASSERTION336 4 61

Hetu

A high-performance distributed deep learning system targeting large-scale and automated distributed training.

Language:PythonApache-2.0231 70

SGL

A scalable graph learning toolkit for extremely large graph datasets. (WWW'22, 🏆 Best Student Paper Award)

Language:PythonMIT127 4 2

GNN-in-RS

GNN in Recommendation System (ACM Computing Surveys 2022)

77 10

GAMLP

Code of GAMLP for Open Graph Benchmark. KDD‘22

Language:Python57 20

mindware

An efficient open-source AutoML system for automating machine learning lifecycle, including feature engineering, neural architecture search, and hyper-parameter tuning.

Language:PythonMIT47 30

2021_AIAC_Task2_1st

QQ浏览器2021AI算法大赛赛道二第1名方案. Rank 1st solution to QQ Browser 2021 AI Algorithm Competition (CIKM AnalytiCup 2021) Track 2 Automated Hyperparameter Optimization.

Language:Python26 30

DBTune

A customized and efficient database tuning system [VLDB'22]

Language:PythonNOASSERTION21 4 1

KnobsTuningEA

An Experimental Evaluation for Database Configuration Tuning

Language:ReScript16 4 2

2021_CCF_BDCI_LargeBERT_Rank1st

Language:CudaApache-2.08 30

HyperTune

Efficient Hyper-parameter Tuning at Scale (VLDB'22)

Language:Python8 20

DGMLP

Language:Python7 10

Hetu-Galvatron

Galvatron is an automatic distributed training system designed for Transformer models, including Large Language Models (LLMs).

Language:Python701

AIR

Language:Python6 10

IGP

Active Learning for GNN (ICLR'22)

5 10

MFES-HB

Implementation of MFES-HB [AAAI'21] along with Hyperband and BOHB

Language:PythonMIT5 30

NAFS

ICML‘22 NAFS

Language:Python5 10

SSD

Transfer Learning based Search Space Design for Hyperparameter Tuning [SIGKDD'22]

Language:Python4 50

HGAMLP

HGAMLP: A Scalable Training Framework for Heterogeneous Graph Neural Networks

Language:Python2 60

DFG-NAS

ICML‘22 DF-GNAS

Language:Python1 10

Lasagne

Lasagne: A Multi-Layer Graph Convolutional Network Framework via Node-aware Deep Architecture [TKDE 2021]

Language:Python1 10

nnfusion

A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description. [OSDI 2020]

Language:C++MIT1 10

RAG-Survey

Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".

100