no code implementations • 11 Mar 2024 • Chaochao Chen, Yizhao Zhang, Yuyuan Li, Dan Meng, Jun Wang, Xiaoli Zheng, Jianwei Yin
The first component is distinguishability loss, where we design a distribution-based measurement to make attribute labels indistinguishable from attackers.
no code implementations • 27 Nov 2023 • Biao Gong, Siteng Huang, Yutong Feng, Shiwei Zhang, Yuyuan Li, Yu Liu
To align the generated image with layout instructions, we present a training-free layout calibration system SimM that intervenes in the generative process on the fly during inference time.
no code implementations • 6 Oct 2023 • Yuyuan Li, Chaochao Chen, Xiaolin Zheng, Yizhao Zhang, Zhongxuan Han, Dan Meng, Jun Wang
To address the PoT-AU problem in recommender systems, we design a two-component loss function that consists of i) distinguishability loss: making attribute labels indistinguishable from attackers, and ii) regularization loss: preventing drastic changes in the model that result in a negative impact on recommendation performance.
no code implementations • 4 Sep 2023 • Zhongxuan Han, Chaochao Chen, Xiaolin Zheng, Weiming Liu, Jun Wang, Wenjie Cheng, Yuyuan Li
By combining the fairness loss with the original backbone model loss, we address the UOF issue and maintain the overall recommendation performance simultaneously.
no code implementations • 7 Jul 2023 • Yuyuan Li, Chaochao Chen, Xiaolin Zheng, Jiaming Zhang
To this end, we propose a novel federated unlearning framework based on incremental learning, which is independent of specific models and federated settings.
no code implementations • 20 Apr 2023 • Yuyuan Li, Chaochao Chen, Xiaolin Zheng, Yizhao Zhang, Biao Gong, Jun Wang
In this paper, we first identify two main disadvantages of directly applying existing unlearning methods in the context of recommendation, i. e., (i) unsatisfactory efficiency for large-scale recommendation models and (ii) destruction of collaboration across users and items.
1 code implementation • CVPR 2023 • Siteng Huang, Biao Gong, Yulin Pan, Jianwen Jiang, Yiliang Lv, Yuyuan Li, Donglin Wang
Many recent studies leverage the pre-trained CLIP for text-video cross-modal retrieval by tuning the backbone with additional heavy modules, which not only brings huge computational burdens with much more parameters, but also leads to the knowledge forgetting from upstream models.
no code implementations • 22 Mar 2022 • Yuyuan Li, Xiaolin Zheng, Chaochao Chen, Junlin Liu
The basic idea of most recommender systems is collaborative filtering, but existing MU methods ignore the collaborative information across users and items.
no code implementations • 13 Nov 2019 • Mengying Zhu, Xiaolin Zheng, Yan Wang, Yuyuan Li, Qianqiao Liang
Also, by constructing multiple strategic arms, we can obtain the optimal investment portfolio to adapt different investment periods.