Yuting Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yuting Liu has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Guibing Guo
Northeastern University, Shenyang, China
6 shared publications - Enneng Yang
Software College, Northeastern University, Shenyang, China
5 shared publications - Jianzhe Zhao
Software College, Northeastern University, Shenyang, China
4 shared publications - Xingwei Wang
Northeastern University
4 shared publications - Linying Jiang
Software College, Northeastern University, Shenyang, China
3 shared publications - Yizhou Dang
Software College, Northeastern University, Shenyang, China
3 shared publications
Latest Publications
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1466-1475
Data Augmentation as Free Lunch: Exploring the Test-Time Augmentation for Sequential Recommendation
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1466-1475
Open AccessData Augmentation as Free Lunch: Exploring the Test-Time Augmentation for Sequential Recommendation
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 334-346
Graph Representation Learning via Causal Diffusion for Out-of-Distribution Recommendation
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 334-346
Open AccessGraph Representation Learning via Causal Diffusion for Out-of-Distribution Recommendation
- Open Access
- 21 January 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (2) , 1-25
Efficient and Adaptive Recommendation Unlearning: A Guided Filtering Framework to Erase Outdated Preferences
Recommendation unlearning is an emerging task to erase the influences of user-specified data from a trained recommendation model. Most existing research follows the paradigm of partitioning the original dataset into multi-fold and then retraining corresponding sub-models while those influences are totally removed. Despite the effectiveness, two key problems remain unexplored: (i) Existing work becomes inefficient and computationally expensive to retrain all sub-models, especially when facing large amounts of unlearning data. (ii) User preferences are dynamically changing. If users express negative opinions on some interacted items they used to prefer, how can we adaptively erase the outdated preferences behind such transformation from the trained model? Although these unlearning data contain outdated information, there is still a lot of helpful knowledge worth preserving. Existing methods ignore this preservation during unlearning and may remove all the knowledge in the interactions, compromising the final performance. In light of these limitations, we propose a novel unlearning framework called GFEraser, which transforms the unlearning into an efficient guided filtering process to avoid time-consuming retraining and retain beneficial knowledge. Specifically, we develop an intra-user negative sampling strategy to learn the outdated preferences that need to be erased. Under the guidance of differential maximization agreement and attention-based fusion module, the original representations are adaptively filtered and aggregated based on the learned preferences. Besides, we leverage contrastive learning to preserve the invariant user preferences, maintaining the final performance. Finally, we devise a new metric called Ranking Decrease Rate to evaluate the unlearning effect. Experimental results demonstrate that GFEraser can maintain reliable recommendation performance while achieving efficient outdated preferences unlearning, up to 37 \(\times\) acceleration.- 21 January 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 43 (2) , 1-25
Open AccessEfficient and Adaptive Recommendation Unlearning: A Guided Filtering Framework to Erase Outdated Preferences
Recommendation unlearning is an emerging task to erase the influences of user-specified data from a trained recommendation model. Most existing research follows the paradigm of partitioning the original dataset into multi-fold and then retraining corresponding sub-models while those influences are totally removed. Despite the effectiveness, two key problems remain unexplored: (i) Existing work becomes inefficient and computationally expensive to retrain all sub-models, especially when facing large amounts of unlearning data. (ii) User preferences are dynamically changing. If users express negative opinions on some interacted items they used to prefer, how can we adaptively erase the outdated preferences behind such transformation from the trained model? Although these unlearning data contain outdated information, there is still a lot of helpful knowledge worth preserving. Existing methods ignore this preservation during unlearning and may remove all the knowledge in the interactions, compromising the final performance. In light of these limitations, we propose a novel unlearning framework called GFEraser, which transforms the unlearning into an efficient guided filtering process to avoid time-consuming retraining and retain beneficial knowledge. Specifically, we develop an intra-user negative sampling strategy to learn the outdated preferences that need to be erased. Under the guidance of differential maximization agreement and attention-based fusion module, the original representations are adaptively filtered and aggregated based on the learned preferences. Besides, we leverage contrastive learning to preserve the invariant user preferences, maintaining the final performance. Finally, we devise a new metric called Ranking Decrease Rate to evaluate the unlearning effect. Experimental results demonstrate that GFEraser can maintain reliable recommendation performance while achieving efficient outdated preferences unlearning, up to 37 \(\times\) acceleration. - Open Access
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 497-506
Repeated Padding for Sequential Recommendation
Sequential recommendation aims to provide users with personalized suggestions based on their historical interactions. When training sequential models, padding is a widely adopted technique for two main reasons: 1) The vast majority of models can only handle fixed-length sequences; 2) Batch-based training needs to ensure that the sequences in each batch have the same length. The special value 0 is usually used as the padding content, which does not contain the actual information and is ignored in the model calculations. This common-sense padding strategy leads us to a problem that has never been explored in the recommendation field: Can we utilize this idle input space by padding other content to improve model performance and training efficiency further? In this paper, we propose a simple yet effective padding method called Repeated Padding (RepPad). Specifically, we use the original interaction sequences as the padding content and fill it to the padding positions during model training. This operation can be performed a finite number of times or repeated until the input sequences’ length reaches the maximum limit. Our RepPad can be considered as a sequence-level data augmentation strategy. Unlike most existing works, our method contains no trainable parameters or hyperparameters and is a plug-and-play data augmentation operation. Extensive experiments on various categories of sequential models and five real-world datasets demonstrate the effectiveness and efficiency of our approach. The average recommendation performance improvement is up to 60.3% on GRU4Rec and 24.3% on SASRec. We also provide in-depth analysis and explanation of what makes RepPad effective from multiple perspectives. Our datasets and codes are available at https://github.com/KingGugu/RepPad.
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 497-506
Open AccessRepeated Padding for Sequential Recommendation
Sequential recommendation aims to provide users with personalized suggestions based on their historical interactions. When training sequential models, padding is a widely adopted technique for two main reasons: 1) The vast majority of models can only handle fixed-length sequences; 2) Batch-based training needs to ensure that the sequences in each batch have the same length. The special value 0 is usually used as the padding content, which does not contain the actual information and is ignored in the model calculations. This common-sense padding strategy leads us to a problem that has never been explored in the recommendation field: Can we utilize this idle input space by padding other content to improve model performance and training efficiency further? In this paper, we propose a simple yet effective padding method called Repeated Padding (RepPad). Specifically, we use the original interaction sequences as the padding content and fill it to the padding positions during model training. This operation can be performed a finite number of times or repeated until the input sequences’ length reaches the maximum limit. Our RepPad can be considered as a sequence-level data augmentation strategy. Unlike most existing works, our method contains no trainable parameters or hyperparameters and is a plug-and-play data augmentation operation. Extensive experiments on various categories of sequential models and five real-world datasets demonstrate the effectiveness and efficiency of our approach. The average recommendation performance improvement is up to 60.3% on GRU4Rec and 24.3% on SASRec. We also provide in-depth analysis and explanation of what makes RepPad effective from multiple perspectives. Our datasets and codes are available at https://github.com/KingGugu/RepPad.
- 8 June 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 299
Video and audio are images: A cross-modal mixer for original data on video–audio retrieval
- 8 June 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 299
Video and audio are images: A cross-modal mixer for original data on video–audio retrieval
- 17 March 2023
- Published by Springer Nature
- p. 491-507
Bi-directional Contrastive Distillation for Multi-behavior Recommendation
- 17 March 2023
- Published by Springer Nature
- p. 491-507
Bi-directional Contrastive Distillation for Multi-behavior Recommendation