publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2024

  1. paper_rope.png
    What Rotary Position Embedding Can Tell Us: Identifying Query and Key Weights Corresponding to Basic Syntactic or High-level Semantic Information
    Yiting Chen, and Junchi Yan
    In Advances in Neural Information Processing Systems (NeurIPS), 2024
    HTML PDF
  2. paper_matthew.jpg
    Unveiling The Matthew Effect Across Channels: Assessing Layer Width Sufficiency via Weight Norm Variance
    Yiting Chen, Jiazi Bu, and Junchi Yan
    In Advances in Neural Information Processing Systems (NeurIPS), 2024
    HTML PDF
  3. paper_going.png
    Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory
    Yiting Chen, Zhanpeng Zhou, and Junchi Yan
    In International Conference on Learning Representations (ICLR), 2024
    HTML
  4. Graph Out-of-Distribution Detection Goes Neighborhood Shaping
    Tianyi Bao, Qitian Wu, Zetian Jiang, and 3 more authors
    In International Conference on Machine Learning (ICML), 2024
    HTML

2023

  1. Energy-based out-of-distribution detection for graph neural networks
    Qitian Wu, Yiting Chen, Chenxiao Yang, and 1 more author
    International Conference on Learning Representations (ICLR), 2023
    HTML
  2. Towards one-shot neural combinatorial solvers: Theoretical and empirical notes on the cardinality-constrained case
    Runzhong Wang, Li Shen, Yiting Chen, and 3 more authors
    In International Conference on Learning Representations (ICLR), 2023
    HTML

2022

  1. paper_shapley.png
    Rethinking and Improving Robustness of Convolutional Neural Networks: a Shapley Value-based Approach in Frequency Domain
    Yiting Chen, Qibing Ren, and Junchi Yan
    In Advances in Neural Information Processing Systems (NeurIPS), 2022
    HTML
  2. Dice: Domain-attack invariant causal learning for improved data privacy protection and adversarial robustness
    Qibing Ren, Yiting Chen, Yichuan Mo, and 2 more authors
    In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2022
    HTML