Ping Li

FedSKETCH: Communication-Efficient and Private Federated Learning via Sketching

2020 · arXiv (Cornell University)

Communication complexity and privacy are the two key challenges in Federated Learning where the goal is to perform a distributed learning through a large volume of devices. In this work, we introduce FedSKETCH and FedSKETCHGATE …

Efficient Learning to Learn a Robust CTR Model for Web-scale Online Sponsored Search Advertising

2021

Click-through rate (CTR) prediction is crucial for online sponsored search advertising. Several successful CTR models have been adopted in the industry, including the regularized logistic regression (LR). Nonetheless, the learning process suffers from two limitations: …

On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyond

2022 · arXiv (Cornell University)

The FedProx algorithm is a simple yet powerful distributed proximal point optimization method widely used for federated learning (FL) over heterogeneous data. Despite its popularity and remarkable success witnessed in practice, the theoretical understanding of …

EOSIOAnalyzer: An Effective Static Analysis Vulnerability Detection Framework for EOSIO Smart Contracts

2022 · 2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)

EOSIO smart contracts are programs that can be collectively executed by a network of mutually untrusted nodes. As EOSIO smart contracts manage valuable assets, they become high-value targets and are subjected to more and more …

Research on geospatial data visualization based on GIS and reverse proxy

2022 · 2022 3rd International Conference on Geology, Mapping and Remote Sensing (ICGMRS)

Based on the practical work, this paper discusses the current visualization techniques of geospatial data. Based on the traditional method of publishing geospatial data service by GIS server, when the data service has been published, …

Towards Deeper Understanding of Variational Auto-encoders for Binary Collaborative Filtering

2022

Recommendation systems are an integral component of machine learning, wherein collaborative filtering (CF) is among the most prominent algorithms employed. Recently, variational auto-encoders (VAEs) with multinomial likelihood and weighted Kullback-Leibler (KL) regularization (referred to as …

Minimization by Incremental Stochastic Surrogate Optimization for Large Scale Nonconvex Problems

2022 · HAL (Le Centre pour la Communication Scientifique Directe)

International audience

Adversarial Attacks on Video Object Segmentation with Hard Region Discovery

2023 · arXiv (Cornell University)

Video object segmentation has been applied to various computer vision tasks, such as video editing, autonomous driving, and human-robot interaction. However, the methods based on deep neural networks are vulnerable to adversarial examples, which are …

Knowledge Graph Embedding Based Question Answering

2019

Question answering over knowledge graph (QA-KG) aims to use facts in the knowledge graph (KG) to answer natural language questions. It helps end users more efficiently and more easily access the substantial and valuable knowledge …