Search Results for author: Ziqi Zhao

Found 11 papers, 8 papers with code

Geminio: Language-Guided Gradient Inversion Attacks in Federated Learning

1 code implementation22 Nov 2024 Junjie Shan, Ziqi Zhao, Jialin Lu, Rui Zhang, Siu Ming Yiu, Ka-Ho Chow

This is achieved by leveraging a pretrained VLM to guide the optimization of a malicious global model that, when shared with and optimized by a victim, retains only gradients of samples that match the attacker-specified query.

Federated Learning

AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection

1 code implementation21 Nov 2024 Jialin Lu, Junjie Shan, Ziqi Zhao, Ka-Ho Chow

Extensive experiments demonstrate that AnywhereDoor provides attackers with a high degree of control, achieving an attack success rate improvement of nearly 80% compared to adaptations of existing methods for such flexible control.

Backdoor Attack Disentanglement +3

Semi-adaptive Synergetic Two-way Pseudoinverse Learning System

1 code implementation27 Jun 2024 Binghong Liu, Ziqi Zhao, Shupan Li, Ke Wang

The whole system is trained using a non-gradient descent learning algorithm.

Offline Trajectory Generalization for Offline Reinforcement Learning

no code implementations16 Apr 2024 Ziqi Zhao, Zhaochun Ren, Liu Yang, Fajie Yuan, Pengjie Ren, Zhumin Chen, Jun Ma, Xin Xin

Then we propose four strategies to use World Transformers to generate high-rewarded trajectory simulation by perturbing the offline data.

D4RL Data Augmentation +4

On the Effectiveness of Unlearning in Session-Based Recommendation

1 code implementation22 Dec 2023 Xin Xin, Liu Yang, Ziqi Zhao, Pengjie Ren, Zhumin Chen, Jun Ma, Zhaochun Ren

On the one hand, these approaches cannot achieve satisfying unlearning effects due to the collaborative correlations and sequential connections between the unlearning item and the remaining items in the session.

Session-Based Recommendations

Generalizing Few-Shot Named Entity Recognizers to Unseen Domains with Type-Related Features

1 code implementation15 Oct 2023 Zihan Wang, Ziqi Zhao, Zhumin Chen, Pengjie Ren, Maarten de Rijke, Zhaochun Ren

To address this limitation, recent studies enable generalization to an unseen target domain with only a few labeled examples using data augmentation techniques.

Data Augmentation few-shot-ner +5

FIS-ONE: Floor Identification System with One Label for Crowdsourced RF Signals

1 code implementation12 Jul 2023 Weipeng Zhuo, Ka Ho Chiu, Jierun Chen, Ziqi Zhao, S. -H. Gary Chan, Sangtae Ha, Chul-Ho Lee

To build a prediction model to identify the floor number of a new RF signal upon its measurement, conventional approaches using the crowdsourced RF signals assume that at least few labeled signal samples are available on each floor.

Combinatorial Optimization Graph Neural Network +2

Interpretation of Time-Series Deep Models: A Survey

no code implementations23 May 2023 Ziqi Zhao, Yucheng Shi, Shushan Wu, Fan Yang, WenZhan Song, Ninghao Liu

Deep learning models developed for time-series associated tasks have become more widely researched nowadays.

Survey Time Series

Coarse-to-Fine Knowledge-Enhanced Multi-Interest Learning Framework for Multi-Behavior Recommendation

no code implementations3 Aug 2022 Chang Meng, Ziqi Zhao, Wei Guo, Yingxue Zhang, Haolun Wu, Chen Gao, Dong Li, Xiu Li, Ruiming Tang

More specifically, we propose a novel Coarse-to-fine Knowledge-enhanced Multi-interest Learning (CKML) framework to learn shared and behavior-specific interests for different behaviors.

Robust Binary Models by Pruning Randomly-initialized Networks

1 code implementation3 Feb 2022 Chen Liu, Ziqi Zhao, Sabine Süsstrunk, Mathieu Salzmann

In this paper, we introduce an approach to obtain robust yet compact models by pruning randomly-initialized binary networks.

Cannot find the paper you are looking for? You can Submit a new open access paper.