Some Practice for Improving the Search Results of E-commerce

1 code implementation • 30 Jul 2022 • Fanyou Wu, Yang Liu, Rado Gazo, Benes Bedrich, Xiaobo Qu

In the Amazon KDD Cup 2022, we aim to apply natural language processing methods to improve the quality of search results that can significantly enhance user experience and engagement with search engines for e-commerce.

TLab: Traffic Map Movie Forecasting Based on HR-NET

no code implementations • 13 Nov 2020 • Fanyou Wu, Yang Liu, Zhiyuan Liu, Xiaobo Qu, Rado Gazo, Eva Haviarova

In our 2020 Competition solution, we further design multiple variants based on HR-NET and UNet.

Feature Engineering

Efficient Project Gradient Descent for Ensemble Adversarial Attack

1 code implementation • 7 Jun 2019 • Fanyou Wu, Rado Gazo, Eva Haviarova, Bedrich Benes

Consider $l_2$ norms attacks, Project Gradient Descent (PGD) and the Carlini and Wagner (C\&W) attacks are the two main methods, where PGD control max perturbation for adversarial examples while C\&W approach treats perturbation as a regularization term optimized it with loss function together.

Adversarial Attack