Pinned Repositories
cnn-dogs-vs-cats
Implementation of cats-vs-dogs based on CNN.
FedPer
PyTorch implementation of FedPer (Federated Learning with Personalization Layers).
FedProx-PyTorch
PyTorch implementation of FedProx (Federated Optimization for Heterogeneous Networks, MLSys 2020).
GNNs-for-Link-Prediction
Some GNNs are implemented using PyG for link prediction tasks, including: GCN, GraphSAGE, GAT, Node2Vec、RGCN、HGT and HAN, which will continue to be updated in the future.
GNNs-for-Node-Classification
Some GNNs are implemented using PyG for node classification tasks, including: GCN, GraphSAGE, SGC, GAT, R-GCN and HAN (Heterogeneous Graph Attention Network), which will continue to be updated in the future.
LSTM-Load-Forecasting
Implementation of Electric Load Forecasting Based on LSTM(BiLSTM). Including Univariate-SingleStep forecasting, Multivariate-SingleStep forecasting and Multivariate-MultiStep forecasting.
LSTM-MultiStep-Forecasting
Implementation of Electric Load Forecasting Based on LSTM (BiLSTM). Including direct-multi-output forecasting, single-step-scrolling forecasting, multi-model-single-step forecasting, multi-model-scrolling forecasting, and seq2seq forecasting.
PyG-GCN
PyG implementation of GCN (Semi-Supervised Classification with Graph Convolutional Networks, ICLR 2017).Datasets: CiteSeer, Cora, PubMed, NELL.
Scaffold-Federated-Learning
PyTorch implementation of SCAFFOLD (Stochastic Controlled Averaging for Federated Learning, ICML 2020).
pytorch_geometric
Graph Neural Network Library for PyTorch
ki-ljl's Repositories
ki-ljl/LSTM-Load-Forecasting
Implementation of Electric Load Forecasting Based on LSTM(BiLSTM). Including Univariate-SingleStep forecasting, Multivariate-SingleStep forecasting and Multivariate-MultiStep forecasting.
ki-ljl/GNNs-for-Node-Classification
Some GNNs are implemented using PyG for node classification tasks, including: GCN, GraphSAGE, SGC, GAT, R-GCN and HAN (Heterogeneous Graph Attention Network), which will continue to be updated in the future.
ki-ljl/FedProx-PyTorch
PyTorch implementation of FedProx (Federated Optimization for Heterogeneous Networks, MLSys 2020).
ki-ljl/LSTM-MultiStep-Forecasting
Implementation of Electric Load Forecasting Based on LSTM (BiLSTM). Including direct-multi-output forecasting, single-step-scrolling forecasting, multi-model-single-step forecasting, multi-model-scrolling forecasting, and seq2seq forecasting.
ki-ljl/cnn-dogs-vs-cats
Implementation of cats-vs-dogs based on CNN.
ki-ljl/FedPer
PyTorch implementation of FedPer (Federated Learning with Personalization Layers).
ki-ljl/Scaffold-Federated-Learning
PyTorch implementation of SCAFFOLD (Stochastic Controlled Averaging for Federated Learning, ICML 2020).
ki-ljl/PyG-GCN
PyG implementation of GCN (Semi-Supervised Classification with Graph Convolutional Networks, ICLR 2017).Datasets: CiteSeer, Cora, PubMed, NELL.
ki-ljl/Per-FedAvg
PyTorch implementation of Per-FedAvg (Personalized Federated Learning: A Meta-Learning Approach).
ki-ljl/GNNs-for-Link-Prediction
Some GNNs are implemented using PyG for link prediction tasks, including: GCN, GraphSAGE, GAT, Node2Vec、RGCN、HGT and HAN, which will continue to be updated in the future.
ki-ljl/FedAvg-numpy-pytorch-tff
Three implementations of FedAvg: numpy, pytorch and tensorflow federated.
ki-ljl/CNN-Load-Forecasting
Implementation of Electric Load Forecasting Based on CNN.
ki-ljl/ncepu-edm
NCEPU-EDM（NCEPU和EDM分别是华北电力大学和教育数据挖掘的缩写）软件是专门为华北电力大学本科生所开发的一款简单软件，具有查询和数据挖掘两大功能模块。其中查询模块为学生提供成绩、课表、考试、GPA、培养方案、成绩总表以及综合测评等教务查询。同时该模块对学生的成绩数据进行可视化分析，包括成绩占比、成绩比较、GPA走势、单科分析、专业排名、挂科分析、单科排名以及个人分析查询。数据挖掘模块对近五年的学生成绩数据进行了关联分析，生成了几十条有用的关联规则，利用关联规则学生可以根据以前考试科目的成绩来大致预测将来考试科目的成绩。同时该模块根据关联规则，选取了关联性较强的一些科目，利用部分科目的成绩来预测特定科目的成绩，并用SVM、KNN等六个机器学习算法来训练模型，进而预测相关成绩，让学生可以根据预测情况进行相应学习状态或者复习状态的调整，最终达到成绩预警的作用。
ki-ljl/AT89C52-examples
AT89C52单片机实验程序：发光二极管的亮灭、多个发光二极管分组循环交替亮灭、外部中断控制数码管循环显示0~9、定时器控制发光二极管的亮灭+简单输出连续矩形脉冲。
ki-ljl/ki-ljl
ki-ljl/LSTM-IMDB-Classification
Use PyTorch to build an LSTM model for text classification on the IMDB dataset.
ki-ljl/POFD
Pytorch Code for NeurIPS 2023 Paper---Public Opinion Field Effect Fusion in Representation Learning for Trending Topics Diffusion.
ki-ljl/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
ki-ljl/CSSummerCamp2022
关于2022年CS保研夏令营通知公告的汇总。欢迎大家积极分享夏令营信息，资瓷一下互联网精神吼不吼啊？
ki-ljl/pytorch_geometric
Graph Neural Network Library for PyTorch
ki-ljl/WeightWatcher
The WeightWatcher tool for predicting the accuracy of Deep Neural Networks
ki-ljl/GNNPapers
Must-read papers on graph neural networks (GNN)
ki-ljl/HLI
Pytorch Code for ICDM 2023 Paper---Hierarchical Label Inference Incorporating Attribute Semantics in Attributed Networks.
ki-ljl/ivy
The Unified Machine Learning Framework
ki-ljl/LINE
LINE: Large-scale Information Network Embedding in PyTorch
ki-ljl/OpenHGNN
This is an open-source toolkit for Heterogeneous Graph Neural Network(OpenHGNN) based on DGL.
ki-ljl/abdockgen
ki-ljl/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.
ki-ljl/POFHP
Pytorch Code for AAAI 2025 Paper---Public Opinion Field Effect and Hawkes Process Join Hands for Information Popularity Prediction.
ki-ljl/pytorch_geometric_temporal
PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)