Yudi Xiong

YudiXiong.github.io. AcadHomepage: A Modern and Responsive Academic Personal Homepage

TIGER. [Pytorch] Unofficial Implementation of "Recommender Systems with Generative Retrieval"

RQ-VAE-Recommender. [Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with Generative Retrieval"

PyTorchOT. implements optimal transport algorithms in pytorch

recommender-systems. This repository contains several state-of-the-art models of recommender system created using the PyTorch framework.

PINet. sigir2019_π-Net: A Parallel Information-sharing Network for Shared account Cross-domain Sequential Recommendations

GA-DTCDR. This is the model in "A Graphical and Attentional Framework for Dual-Target Cross-Domain Recommendation" (IJCAI2020). GA-DTCDR is an optimized model for DTCDR ("DTCDR: A Framework for Dual-Target Cross-Domain Recommendation" in CIKM2019).

hgnn. Hyperbolic Graph Neural Networks

RecBook. 推荐系统修炼手册

RSPapers. RSTutorials: A Curated List of Must-read Papers on Recommender System.

ROT. Code for Watch and Match: Supercharging Imitation with Regularized Optimal Transport

Awesome-LLM4RS-Papers. Large Language Model-enhanced Recommender System Papers

Graph-Optimal-Transport. Code for ICML 2020 "Graph Optimal Transport for Cross-Domain Alignment"

KernelNeuralOptimalTransport. PyTorch implementation of "Kernel Neural Optimal Transport" (ICLR 2023)

NeuralOptimalTransport. PyTorch implementation of "Neural Optimal Transport" (ICLR 2023 Spotlight)

POT. POT : Python Optimal Transport

adversarial-recommender-systems-survey. The goal of this survey is two-fold: (i) to present recent advances on adversarial machine learning (AML) for the security of RS (i.e., attacking and defense recommendation models), (ii) to show another successful application of AML in generative adversarial networks (GANs) for generative applications, thanks to their ability for learning (high-dimensional) data distributions. In this survey, we provide an exhaustive literature review of 74 articles published in major RS and ML journals and conferences. This review serves as a reference for the RS community, working on the security of RS or on generative models using GANs to improve their quality.

ARLib. An open-source framework for conducting data poisoning attacks on recommendation systems, designed to assist researchers and practitioners.

awesome-recsys-poisoning. A Survey of Poisoning Attacks and Defenses in Recommender Systems

FedRec. [AAAI 2023] Official PyTorch implementation for "Untargeted Attack against Federated Recommendation Systems via Poisonous Item Embeddings and the Defense"

revisit_adv_rec. A PyTorch implementation for the Recsys 2020 paper: Revisiting Adversarially Learned Injection Attacks Against Recommender Systems

sif_mi_attack. Membership Inference Attack Using Self Influence Functions

RAPU. [KDD'21] Official PyTorch implementation for "Data Poisoning Attack against Recommender System Using Incomplete and Perturbed Data".

Recommendation-Attack-Survey. Survey on the recommendation attack topic, continuing to update.

UC-FedRec. Source Code for WSDM paper "User Consented Federated Recommender System Against Personalized Attribute Inference Attack"

PracticalGuidetoRecSys. 《互联网大厂推荐算法实战》资料库

leetcode-master. 《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

kamacoder-solutions. 卡码网题解全集

MLE-interview. 该仓库记录搜索推荐算法工程师的必备面试知识点+paper

Privacy-Attacks-in-Machine-Learning. Membership Inference, Attribute Inference and Model Inversion attacks implemented using PyTorch.

fed2tier. Fed2Tier offers a two-tier federated learning approach, optimizing for eco-friendliness and efficiency. It improves model generalizability by integrating more edge devices and uniquely categorizing clients. The addition of intermediate nodes streamlines communication and reduces carbon emissions, enhancing both privacy and performance.

fedpc. A Federated Deep Learning Framework for Privacy Preservation and Communication Efficiency  

Splitting-training-A-Federated-Learning-on-Different-Feature-Space-with-Efficiency.

VFL-CZOFO. Implementation for NIPS2023: A Unified Solution for Privacy and Communication Efficiency in Vertical Federated Learning

federated-learning-in-wireless-communication-paper-survey. Some paper about federated learning in wireless communication system. The papers discuss the issues about client selection ( user scheduling), resource allocation and some new communication efficiency framework.

fed-unlearn. An Empirical Study of Federated Unlearning: Efficiency and Effectiveness (Accepted Conference Track Papers at ACML 2023)

Net_Sec_Final_Proj. simulation in python of algorithm proposed in "An Efficiency-Boosting Client Selection Scheme for Federated Learniing With Fairness Guarantee" by Tiansheng Huang, Weiwei Lin, Member, IEEE, Wentai Wu, Ligang He, Keqin Li, Fellow, IEEE, and Albert Y. Zomaya

Federated-Learning-in-Gaze-Recognition. The efficiency and generalizability of a deep learning model is based on the amount and diversity of training data. Although huge amounts of data are being collected, these data are not stored in centralized servers for further data processing. It is often infeasible to collect and share data in centralized servers due to various medical data regulations. This need for diversely distributed data and infeasible storage solutions calls for Federated Learning (FL). FL is a clever way of utilizing privately stored data in model building without the need for data sharing. The idea is to train several different models locally with the same architecture, share the model weights between the collaborators, aggregate the model weights and use the resulting global weights in furthering model building. FL is an iterative algorithm that repeats the above steps over a defined number of rounds. By doing so, we negate the need for centralized data sharing and avoid several regulations tied to it. In this work, federated learning is applied to gaze recognition, a task to identify where the doctor’s gaze at. A global model is built by repeatedly aggregating local models built from 8 local institutional data using the FL algorithm for 4 federated rounds. The results show an increase in the performance of the global model over federated rounds. The study also shows that the global model can be trained one more time locally at the end of FL on each institutional level to fine-tune the model to local data.

AsynchronousFL-Simulator. Asychronous Federated Learning Simulator for testing the efficiency of sync and async FL.

VerticalFederatedEfficiency. THU-AIR 联邦学习 通信和效率