Search Results for author:
Found 10 papers, 4 papers with code
Repeated Padding as Data Augmentation for Sequential Recommendation
Specifically, we use the original interaction sequences as the padding content and fill it to the padding positions during model training.
Representation Surgery for Multi-Task Model Merging
That is, there is a significant discrepancy in the representation distribution between the merged and individual models, resulting in poor performance of merged MTL.
ID Embedding as Subtle Features of Content and Structure for Multimodal Recommendation
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.
AdaMerging: Adaptive Model Merging for Multi-Task Learning
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.
Continual Learning From a Stream of APIs
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.
A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning
Through this comprehensive survey, we aspire to uncover potential solutions by drawing upon ideas and approaches from various fields that have dealt with forgetting.
Data Augmented Flatness-aware Gradient Projection for Continual Learning
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.
Uniform Sequence Better: Time Interval Aware Data Augmentation for Sequential Recommendation
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}.
AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning
In this paper, we propose to measure the task dominance degree of a parameter by the total updates of each task on this parameter.
Generalized Embedding Machines for Recommender Systems
In this work, we propose an alternative approach to model high-order interaction signals in the embedding level, namely Generalized Embedding Machine (GEM).
