Xinyi Wu

Orcid: 0009-0007-9804-2012

Affiliations:
  • Massachusetts Institute of Technology (MIT), Institute for Data, Systems, and Society, Cambridge, USA


According to our database1, Xinyi Wu authored at least 10 papers between 2022 and 2025.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
On the Emergence of Position Bias in Transformers.
CoRR, February, 2025

GraphHash: Graph Clustering Enables Parameter Efficiency in Recommender Systems.
Proceedings of the ACM on Web Conference 2025, 2025

Understanding and Scaling Collaborative Filtering Optimization from the Perspective of Matrix Rank.
Proceedings of the ACM on Web Conference 2025, 2025

Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
GraphHash: Graph Clustering Enables Parameter Efficiency in Recommender Systems.
CoRR, 2024

On the Role of Attention Masks and LayerNorm in Transformers.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

2023
Demystifying Oversmoothing in Attention-Based Graph Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

A Non-Asymptotic Analysis of Oversmoothing in Graph Neural Networks.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022
A Non-Asymptotic Analysis of Oversmoothing in Graph Neural Networks.
CoRR, 2022

Link Partitioning on Simplicial Complexes Using Higher-Order Laplacians.
Proceedings of the IEEE International Conference on Data Mining, 2022


  Loading...