Yuhang Wu
Research Subjects
Yuhang Wu has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Hanghang Tong
University of Illinois Urbana-Champaign, Urbana, IL, USA
2 shared publications - Hao Yang
Visa Research, Palo Alto, CA, USA
2 shared publications - Ioannis A. Kakadiaris
Department of Computer Science, University of Houston, Houston, TX 77204, USA
2 shared publications - Menghai Pan
Visa Research, Foster City, CA, USA
2 shared publications - Qinghai Zhou
Meta Platforms, Sunnyvale, CA, USA
2 shared publications - Yuzhong Chen
Visa Research, Foster City, CA, USA
2 shared publications
Latest Publications
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3494-3504
Graph Anomaly Detection with Adaptive Node Mixup
Graph anomaly detection (GAD) aims to find network elements (e.g., nodes, edges) with significantly atypical patterns and has a profound impact in a variety of application domains, including social network analysis, security, Web, finance, and many more. Most of the existing methods have been developed in an unsupervised manner or with extremely limited supervision, due to the high cost of acquiring ground-truth information. Consequently, the identified anomalies may turn out to be noises or uneventful instances because of the lack of prior knowledge on graph anomalies. To address the data scarcity issue in GAD, in this paper, we propose, gADAM, a novel graph neural network-based GAD framework, which consolidates (1) an innovative mixup approach to augment the original training data by adaptively interpolating data instances in the embedding space, and (2) an efficacious sampling method to obtain high-quality negative samples for model training. Additionally, to advance the representation learning for GAD, we further equip the proposed framework with a generic prototype-based learning module. Through extensive empirical evaluations, we corroborate the superiority of the proposed gADAM framework on graph anomaly detection w.r.t. various metrics.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3494-3504
Open AccessGraph Anomaly Detection with Adaptive Node Mixup
Graph anomaly detection (GAD) aims to find network elements (e.g., nodes, edges) with significantly atypical patterns and has a profound impact in a variety of application domains, including social network analysis, security, Web, finance, and many more. Most of the existing methods have been developed in an unsupervised manner or with extremely limited supervision, due to the high cost of acquiring ground-truth information. Consequently, the identified anomalies may turn out to be noises or uneventful instances because of the lack of prior knowledge on graph anomalies. To address the data scarcity issue in GAD, in this paper, we propose, gADAM, a novel graph neural network-based GAD framework, which consolidates (1) an innovative mixup approach to augment the original training data by adaptively interpolating data instances in the embedding space, and (2) an efficacious sampling method to obtain high-quality negative samples for model training. Additionally, to advance the representation learning for GAD, we further equip the proposed framework with a generic prototype-based learning module. Through extensive empirical evaluations, we corroborate the superiority of the proposed gADAM framework on graph anomaly detection w.r.t. various metrics.
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 2862-2873
Node Classification Beyond Homophily: Towards a General Solution
Graph neural networks (GNNs) have become core building blocks behind a myriad of graph learning tasks. The vast majority of the existing GNNs are built upon, either implicitly or explicitly, the homophily assumption, which is not always true and could heavily degrade the performance of learning tasks. In response, GNNs tailored for heterophilic graphs have been developed. However, most of the existing works are designed for the specific GNN models to address heterophily, which lacks generality. In this paper, we study the problem from the structure learning perspective and propose a family of general solutions named ALT. It can work hand in hand with most of the existing GNNs to handle graphs with either low or high homophily. At the core of our method is learning to (1) decompose a given graph into two components, (2) extract complementary graph signals from these two components, and (3) adaptively integrate the graph signals for node classification. Moreover, analysis based on graph signal processing shows that our framework can empower a broad range of existing GNNs to have adaptive filter characteristics and further modulate the input graph signals, which is critical for handling complex homophilic/heterophilic patterns. The proposed ALT brings significant and consistent performance improvement in node classification for a wide range of GNNs over a variety of real-world datasets.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 2862-2873
Open AccessNode Classification Beyond Homophily: Towards a General Solution
Graph neural networks (GNNs) have become core building blocks behind a myriad of graph learning tasks. The vast majority of the existing GNNs are built upon, either implicitly or explicitly, the homophily assumption, which is not always true and could heavily degrade the performance of learning tasks. In response, GNNs tailored for heterophilic graphs have been developed. However, most of the existing works are designed for the specific GNN models to address heterophily, which lacks generality. In this paper, we study the problem from the structure learning perspective and propose a family of general solutions named ALT. It can work hand in hand with most of the existing GNNs to handle graphs with either low or high homophily. At the core of our method is learning to (1) decompose a given graph into two components, (2) extract complementary graph signals from these two components, and (3) adaptively integrate the graph signals for node classification. Moreover, analysis based on graph signal processing shows that our framework can empower a broad range of existing GNNs to have adaptive filter characteristics and further modulate the input graph signals, which is critical for handling complex homophilic/heterophilic patterns. The proposed ALT brings significant and consistent performance improvement in node classification for a wide range of GNNs over a variety of real-world datasets.
- Open Access
- 1 April 2022
- Published by KEAI Publishing in Defence Technology
- Vol. 18 (4) , 663-677
An optimized run-length based algorithm for sparse remote sensing image labeling
- 1 April 2022
- Published by KEAI Publishing in Defence Technology
- Vol. 18 (4) , 663-677
Open AccessAn optimized run-length based algorithm for sparse remote sensing image labeling
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 1 (4) , 264-277
3-D Face Alignment Using A Convolutional Point-Set Representation
We present a robust method for estimating the facial pose and shape parameters with a Projected Normalized Coordinate Code (PNCC), a derived image where each pixel is annotated with its corresponding vertex position in a generic 3D model. The method relies on a Convolutional Point-set Representation (CPR), a carefully designed feature map that extracts useful information encoded in pairs or triplets of vertices of PNCC. To estimate the shape and pose parameters, different CPRs are designed to represent mutually independent pose and shape parameters. The CPRs are then fed into multiple convolutional networks (with recurrent layers) in a sequential manner based on the transformation order of weak-perspective projection model to predict the target parameters. Reprojection errors are sampled along a predicted direction and the parameters are updated based on the pattern of reprojection errors. This technique boosts the model’s capability to find a local minimum under challenging scenarios. It is also demonstrated that CPRs obtained from different sources can be merged and contribute to outperforming the current state-of-the-art solutions for 3D face alignment. Experiments indicate that the proposed CPRFA (CPR-based Face Alignment) significantly improves 3D alignment accuracy. Compared to 3DDFA, the proposed method reduces the normalized mean error on AFLW2000 and AFLW database by 25.3 20.2% respectively.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 1 (4) , 264-277
3-D Face Alignment Using A Convolutional Point-Set Representation
We present a robust method for estimating the facial pose and shape parameters with a Projected Normalized Coordinate Code (PNCC), a derived image where each pixel is annotated with its corresponding vertex position in a generic 3D model. The method relies on a Convolutional Point-set Representation (CPR), a carefully designed feature map that extracts useful information encoded in pairs or triplets of vertices of PNCC. To estimate the shape and pose parameters, different CPRs are designed to represent mutually independent pose and shape parameters. The CPRs are then fed into multiple convolutional networks (with recurrent layers) in a sequential manner based on the transformation order of weak-perspective projection model to predict the target parameters. Reprojection errors are sampled along a predicted direction and the parameters are updated based on the pattern of reprojection errors. This technique boosts the model’s capability to find a local minimum under challenging scenarios. It is also demonstrated that CPRs obtained from different sources can be merged and contribute to outperforming the current state-of-the-art solutions for 3D face alignment. Experiments indicate that the proposed CPRFA (CPR-based Face Alignment) significantly improves 3D alignment accuracy. Compared to 3DDFA, the proposed method reduces the normalized mean error on AFLW2000 and AFLW database by 25.3 20.2% respectively.
- 1 May 2018
- Published by Elsevier in Image and Vision Computing
- Vol. 73, 1-16
GoDP: Globally Optimized Dual Pathway deep network architecture for facial landmark localization in-the-wild
- 1 May 2018
- Published by Elsevier in Image and Vision Computing
- Vol. 73, 1-16
GoDP: Globally Optimized Dual Pathway deep network architecture for facial landmark localization in-the-wild