1 code implementation • 13 Mar 2024 • Xuansheng Wu, Haiyan Zhao, Yaochen Zhu, Yucheng Shi, Fan Yang, Tianming Liu, Xiaoming Zhai, Wenlin Yao, Jundong Li, Mengnan Du, Ninghao Liu
Therefore, in this paper, we introduce Usable XAI in the context of LLMs by analyzing (1) how XAI can benefit LLMs and AI systems, and (2) how LLMs can contribute to the advancement of XAI.
1 code implementation • 5 Mar 2024 • Yaochen Zhu, Rui Xia, Jiajun Zhang
In this paper, we introduce a dual-stage method termed Dynamic Pruning Partition Amplification (DPPA), devised to tackle the challenge of merging complex fine-tuned models.
1 code implementation • 2 Nov 2023 • Yaochen Zhu, Liang Wu, Qi Guo, Liangjie Hong, Jundong Li
We first extend the vocabulary of pretrained LLMs with user/item ID tokens to faithfully model user/item collaborative and content semantics.
no code implementations • 24 Oct 2023 • Song Wang, Yaochen Zhu, Haochen Liu, Zaiyi Zheng, Chen Chen, Jundong Li
Afterward, we provide an innovative taxonomy of KME techniques based on how the new knowledge is introduced into pre-trained LLMs, and investigate existing KME strategies while analyzing key insights, advantages, and limitations of methods from each category.
1 code implementation • 5 Jun 2023 • Yaochen Zhu, Jing Ma, Liang Wu, Qi Guo, Liangjie Hong, Jundong Li
But since sensitive features may also affect user interests in a fair manner (e. g., race on culture-based preferences), indiscriminately eliminating all the influences of sensitive features inevitably degenerate the recommendations quality and necessary diversities.
no code implementations • 5 Apr 2023 • Yaochen Zhu, Xiangqing Shen, Rui Xia
For another, the multimodal reasoning task emphasized the prediction of future states and behaviors but often neglected the incorporation of individual personality traits.
1 code implementation • 3 Jan 2023 • Yaochen Zhu, Jing Ma, Jundong Li
Traditional RSs estimate user interests and predict their future behaviors by utilizing correlations in the observational historical activities, their profiles, and the content of interacted items.
1 code implementation • 21 Nov 2022 • Yaochen Zhu, Zhenzhong Chen
However, since latent item variables are not modeled in UAE, it is difficult to utilize the widely available item content information when ratings are sparse.
1 code implementation • 28 May 2022 • Yaochen Zhu, Xubin Ren, Jing Yi, Zhenzhong Chen
We first establish a causal graph to represent the relations among uploader, UGC, and tag, where the uploaders are identified as confounders that spuriously correlate UGC and tag selections.
1 code implementation • 6 Jan 2022 • Yaochen Zhu, Jing Yi, Jiayi Xie, Zhenzhong Chen
As with all observational studies, hidden confounders, which are factors that affect both item exposures and user ratings, lead to a systematic bias in the estimation.
no code implementations • 15 Jul 2021 • Jing Yi, Yaochen Zhu, Jiayi Xie, Zhenzhong Chen
Moreover, the multimodal information is fused by the product-of-experts (PoE) principle, where the semantic information in visual and textual modalities of the micro-video are weighted according to their variance estimations such that the modality with a lower noise level is given more weights.
1 code implementation • 17 May 2021 • Yaochen Zhu, Zhenzhong Chen
Moreover, by considering the fusion of collaborative and feature variables as a virtual communication channel from an information-theoretic perspective, we introduce a user-dependent channel to dynamically control the information allowed to be accessed from the feature embeddings.
1 code implementation • 28 Mar 2020 • Yaochen Zhu, Jiayi Xie, Zhenzhong Chen
As an emerging type of user-generated content, micro-video drastically enriches people's entertainment experiences and social interactions.