no code implementations • 11 Mar 2024 • Yizhou Dang, YuTing Liu, Enneng Yang, Guibing Guo, Linying Jiang, Xingwei Wang, Jianzhe Zhao
Specifically, we use the original interaction sequences as the padding content and fill it to the padding positions during model training.
1 code implementation • 5 Feb 2024 • Enneng Yang, Li Shen, Zhenyi Wang, Guibing Guo, Xiaojun Chen, Xingwei Wang, DaCheng Tao
That is, there is a significant discrepancy in the representation distribution between the merged and individual models, resulting in poor performance of merged MTL.
no code implementations • 10 Nov 2023 • YuTing Liu, Enneng Yang, Yizhou Dang, Guibing Guo, Qiang Liu, Yuliang Liang, Linying Jiang, Xingwei Wang
In this paper, we revisit the value of ID embeddings for multimodal recommendation and conduct a thorough study regarding its semantics, which we recognize as subtle features of content and structures.
1 code implementation • 4 Oct 2023 • Enneng Yang, Zhenyi Wang, Li Shen, Shiwei Liu, Guibing Guo, Xingwei Wang, DaCheng Tao
This approach aims to autonomously learn the coefficients for model merging, either in a task-wise or layer-wise manner, without relying on the original training data.
no code implementations • 31 Aug 2023 • Enneng Yang, Zhenyi Wang, Li Shen, Nan Yin, Tongliang Liu, Guibing Guo, Xingwei Wang, DaCheng Tao
Next, we train the CL model by minimizing the gap between the responses of the CL model and the black-box API on synthetic data, to transfer the API's knowledge to the CL model.
1 code implementation • 16 Jul 2023 • Zhenyi Wang, Enneng Yang, Li Shen, Heng Huang
Through this comprehensive survey, we aspire to uncover potential solutions by drawing upon ideas and approaches from various fields that have dealt with forgetting.
no code implementations • ICCV 2023 • Enneng Yang, Li Shen, Zhenyi Wang, Shiwei Liu, Guibing Guo, Xingwei Wang
In this paper, we first revisit the gradient projection method from the perspective of flatness of loss surface, and find that unflatness of the loss surface leads to catastrophic forgetting of the old tasks when the projection constraint is reduced to improve the performance of new tasks.
1 code implementation • 16 Dec 2022 • Yizhou Dang, Enneng Yang, Guibing Guo, Linying Jiang, Xingwei Wang, Xiaoxiao Xu, Qinghui Sun, Hong Liu
However, we observe that the time interval in a sequence may vary significantly different, and thus result in the ineffectiveness of user modeling due to the issue of \emph{preference drift}.
no code implementations • 28 Nov 2022 • Enneng Yang, Junwei Pan, Ximei Wang, Haibin Yu, Li Shen, Xihua Chen, Lei Xiao, Jie Jiang, Guibing Guo
In this paper, we propose to measure the task dominance degree of a parameter by the total updates of each task on this parameter.
no code implementations • 16 Feb 2020 • Enneng Yang, Xin Xin, Li Shen, Guibing Guo
In this work, we propose an alternative approach to model high-order interaction signals in the embedding level, namely Generalized Embedding Machine (GEM).