Rongzhe Wei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Rongzhe Wei has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Anshumali Shrivastava
Department of Computer Science Rice University
1 shared publication - Can Qin
Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA
1 shared publication - Haoteng Yin
Purdue University, West Lafayette, IN, USA
1 shared publication - Pan Li
Georgia Institute of Technology
1 shared publication - Tianyi Zhang
Visa Research, Foster City, CA, USA
1 shared publication Yi Xu
Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA
1 shared publication
Latest Publications
- 23 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (12) , 9282-9293
SLA2P: Self-Supervised Anomaly Detection With Adversarial Perturbation
Anomaly detection is a fundational yet difficult problem in machine learning. In this work, we propose a new and effective framework, dubbed as SLA $^{2}$ P, for unsupervised anomaly detection. Following the extraction of delegate embeddings from raw data, we implement random projections on the features and consider features transformed by disparate projections as being associated with separate pseudo-classes. We then train a neural network for classification on these transformed features to conduct self-supervised learning. Subsequently, we introduce adversarial disturbances to the modified attributes, and we develop anomaly scores built on the classifier's predictive uncertainties concerning these disrupted features. Our approach is motivated by the fact that as anomalies are relatively rare and decentralized, 1) the training of the pseudo-label classifier concentrates more on acquiring the semantic knowledge of regular data instead of anomalous data; 2) the altered attributes of the normal data exhibit greater resilience to disturbances compared to those of the anomalous data. Therefore, the disrupted modified attributes of anomalies can not be well classified and correspondingly tend to attain lesser anomaly scores. The results of experiments on various benchmark datasets for images, text, and inherently tabular data demonstrate that SLA $^{2}$ P achieves state-of-the-art performance consistently.
- 23 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (12) , 9282-9293
SLA2P: Self-Supervised Anomaly Detection With Adversarial Perturbation
Anomaly detection is a fundational yet difficult problem in machine learning. In this work, we propose a new and effective framework, dubbed as SLA $^{2}$ P, for unsupervised anomaly detection. Following the extraction of delegate embeddings from raw data, we implement random projections on the features and consider features transformed by disparate projections as being associated with separate pseudo-classes. We then train a neural network for classification on these transformed features to conduct self-supervised learning. Subsequently, we introduce adversarial disturbances to the modified attributes, and we develop anomaly scores built on the classifier's predictive uncertainties concerning these disrupted features. Our approach is motivated by the fact that as anomalies are relatively rare and decentralized, 1) the training of the pseudo-label classifier concentrates more on acquiring the semantic knowledge of regular data instead of anomalous data; 2) the altered attributes of the normal data exhibit greater resilience to disturbances compared to those of the anomalous data. Therefore, the disrupted modified attributes of anomalies can not be well classified and correspondingly tend to attain lesser anomaly scores. The results of experiments on various benchmark datasets for images, text, and inherently tabular data demonstrate that SLA $^{2}$ P achieves state-of-the-art performance consistently.
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 980-991
Learning Scalable Structural Representations for Link Prediction with Bloom Signatures
Graph neural networks (GNNs) have shown great potential in learning on graphs, but they are known to perform sub-optimally on link prediction tasks. Existing GNNs are primarily designed to learn node-wise representations and usually fail to capture pairwise relations between target nodes, which proves to be crucial for link prediction. Recent works resort to learning more expressive edge-wise representations by enhancing vanilla GNNs with structural features such as labeling tricks and link prediction heuristics, but they suffer from high computational overhead and limited scalability. To tackle this issue, we propose to learn structural link representations by augmenting the message-passing framework of GNNs with Bloom signatures. Bloom signatures are hashing-based compact encodings of node neighborhoods, which can be efficiently merged to recover various types of edge-wise structural features. We further show that any type of neighborhood overlap-based heuristic can be estimated by a neural network that takes Bloom signatures as input. GNNs with Bloom signatures are provably more expressive than vanilla GNNs and also more scalable than existing edge-wise models. Experimental results on five standard link prediction benchmarks show that our proposed model achieves comparable or better performance than existing edge-wise GNN models while being 3-200x faster and more memory-efficient for online inference. Source code is available at https://github.com/tonyzhang617/BloomSigLP.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 980-991
Open AccessLearning Scalable Structural Representations for Link Prediction with Bloom Signatures
Graph neural networks (GNNs) have shown great potential in learning on graphs, but they are known to perform sub-optimally on link prediction tasks. Existing GNNs are primarily designed to learn node-wise representations and usually fail to capture pairwise relations between target nodes, which proves to be crucial for link prediction. Recent works resort to learning more expressive edge-wise representations by enhancing vanilla GNNs with structural features such as labeling tricks and link prediction heuristics, but they suffer from high computational overhead and limited scalability. To tackle this issue, we propose to learn structural link representations by augmenting the message-passing framework of GNNs with Bloom signatures. Bloom signatures are hashing-based compact encodings of node neighborhoods, which can be efficiently merged to recover various types of edge-wise structural features. We further show that any type of neighborhood overlap-based heuristic can be estimated by a neural network that takes Bloom signatures as input. GNNs with Bloom signatures are provably more expressive than vanilla GNNs and also more scalable than existing edge-wise models. Experimental results on five standard link prediction benchmarks show that our proposed model achieves comparable or better performance than existing edge-wise GNN models while being 3-200x faster and more memory-efficient for online inference. Source code is available at https://github.com/tonyzhang617/BloomSigLP.