Search Results for author:
Found 4 papers, 2 papers with code
FCDNet: Frequency-Guided Complementary Dependency Modeling for Multivariate Time-Series Forecasting
Additionally, adopting a frequency-based perspective can effectively mitigate the influence of noise within MTS data, which helps capture more genuine dependencies.
Individual and Structural Graph Information Bottlenecks for Out-of-Distribution Generalization
To remove class spurious feature caused by distribution shifts, we propose Individual Graph Information Bottleneck (I-GIB) which discards irrelevant information by minimizing the mutual information between the input graph and its embeddings.
Spatial Autoregressive Coding for Graph Neural Recommendation
To adequately leverage neighbor proximity and high-order information, we design a novel spatial autoregressive paradigm.
Fine-grained Interest Matching for Neural News Recommendation
Existing studies generally represent each user as a single vector and then match the candidate news vector, which may lose fine-grained information for recommendation.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
