| Beyond homophily in graph neural networks: Current limitations and effective designs J Zhu, Y Yan, L Zhao, M Heimann, L Akoglu, D Koutra Advances in neural information processing systems 33, 7793-7804, 2020 | 822 | 2020 |
| Pairnorm: Tackling oversmoothing in gnns L Zhao, L Akoglu ICLR 2020, 2019 | 538 | 2019 |
| From stars to subgraphs: Uplifting any GNN with local structure awareness L Zhao, W Jin, L Akoglu, N Shah ICLR 2022, 2021 | 140 | 2021 |
| Sign and basis invariant networks for spectral graph representation learning D Lim, J Robinson, L Zhao, T Smidt ICLR 2023, 2022 | 121* | 2022 |
| Graph condensation for graph neural networks W Jin, L Zhao, S Zhang, Y Liu, J Tang, N Shah ICLR 2022, 2021 | 114 | 2021 |
| Graph unrolling networks: Interpretable neural networks for graph signal denoising S Chen, YC Eldar, L Zhao IEEE Transactions on Signal Processing 69, 3699-3713, 2021 | 65 | 2021 |
| On using classification datasets to evaluate graph outlier detection: Peculiar observations and new insights L Zhao, L Akoglu Big Data 11 (3), 151-180, 2023 | 43 | 2023 |
| Generalizing graph neural networks beyond homophily J Zhu, Y Yan, L Zhao, M Heimann, L Akoglu, D Koutra arXiv preprint arXiv:2006.11468, 2020 | 37 | 2020 |
| A quest for structure: Jointly learning the graph structure and semi-supervised classification X Wu*, L Zhao*, L Akoglu Proceedings of the 27th ACM international conference on information and …, 2018 | 35 | 2018 |
| Hyperparameter sensitivity in deep outlier detection: Analysis and a scalable hyper-ensemble solution X Ding, L Zhao, L Akoglu NeurIPS 2022, 2022 | 19 | 2022 |
| A Practical, Progressively-Expressive GNN L Zhao, L Härtel, N Shah, L Akoglu NeurIPS 2022, 2022 | 17 | 2022 |
| Graph Anomaly Detection with Unsupervised GNNs L Zhao, S Sawlani, A Srinivasan, L Akoglu ICDM 2022 short, 2022 | 13 | 2022 |
| Heterophily and graph neural networks: Past, present and future J Zhu, Y Yan, M Heimann, L Zhao, L Akoglu, D Koutra IEEE Data Engineering Bulletin, 2023 | 6 | 2023 |
| Fast attributed graph embedding via density of states S Sawlani, L Zhao, L Akoglu 2021 IEEE International Conference on Data Mining (ICDM), 559-568, 2021 | 6 | 2021 |
| Connecting graph convolutional networks and graph-regularized pca L Zhao, L Akoglu ICML 2020 Workshop, 2020 | 5 | 2020 |
| DSV: an alignment validation loss for self-supervised outlier model selection J Yoo, Y Zhao, L Zhao, L Akoglu Joint European Conference on Machine Learning and Knowledge Discovery in …, 2023 | 4 | 2023 |
| Improving and Unifying Discrete&Continuous-time Discrete Denoising Diffusion L Zhao*, X Ding*, L Yu, L Akoglu arXiv preprint arXiv:2402.03701, 2024 | 1 | 2024 |
| End-to-End Augmentation Hyperparameter Tuning for Self-Supervised Anomaly Detection J Yoo, L Zhao, L Akoglu arXiv preprint arXiv:2306.12033, 2023 | 1 | 2023 |
| On the Expressive Power of Spectral Invariant Graph Neural Networks B Zhang, L Zhao, H Maron arXiv preprint arXiv:2406.04336, 2024 | | 2024 |
| Descriptive Kernel Convolution Network with Improved Random Walk Kernel MC Lee*, L Zhao*, L Akoglu 2024 WWW, 2024 | | 2024 |
Leman AkogluAssociate Professor, Carnegie Mellon University在 andrew.cmu.edu 的电子邮件经过验证
