Shihao Ji

Shihao Ji

Auto-generated profile, based on publicly available information

Shihao Ji

Georgia State University

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 April 2021 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
YYYang Ye
Yang Ye
SJShihao Ji
Shihao Ji
Graph Neural Networks (GNNs) have proved to be an effective representation learning framework for graph-structured data, and have achieved state-of-the-art performance on many practical predictive tasks. Among the variants of GNNs, Graph Attention Networks (GATs) improve the performance of many graph learning tasks through a dense attention mechanism. However, real-world graphs are often very large and noisy, and GATs are prone to overfitting if not regularized properly. In this paper, we propose Sparse Graph Attention Networks (SGATs) that learn sparse attention coefficients under an L0-norm regularization, and the learned sparse attentions are then used for all GNN layers, resulting in an edge-sparsified graph. By doing so, we can identify noisy/task-irrelevant edges, and thus perform feature aggregation on most informative neighbors. Extensive experiments on synthetic and real-world (assortative and disassortative) graph learning benchmarks demonstrate the superior performance of SGATs. Furthermore, the removed edges can be interpreted intuitively and quantitatively. To the best of our knowledge, this is the first graph learning algorithm that shows significant redundancies in graphs and edge-sparsified graphs can achieve similar (on assortative graphs) or sometimes higher (on disassortative graphs) predictive performances than original graphs. Our code is available at https://github.com/Yangyeeee/SGAT.

6 November 2020 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
KLKaiyang Li
Kaiyang Li
GLGuangchun Luo
Guangchun Luo
YYYang Ye
Yang Ye
Wei LiWei Li
Wei Li
SJShihao Ji
Shihao Ji
ZCZhipeng Cai
Zhipeng Cai
Recently, the surge in popularity of Internet of Things (IoT), mobile devices, social media, etc. has opened up a large source for graph data. Graph embedding has been proved extremely useful to learn low-dimensional feature representations from graph structured data. These feature representations can be used for a variety of prediction tasks from node classification to link prediction. However, existing graph embedding methods do not consider users’ privacy to prevent inference attacks. That is, adversaries can infer users’ sensitive information by analyzing node representations learned from graph embedding algorithms. In this paper, we propose Adversarial Privacy Graph Embedding (APGE), a graph adversarial training framework that integrates the disentangling and purging mechanisms to remove users’ private information from learned node representations. The proposed method preserves the structural information and utility attributes of a graph while concealing users’ private attributes from inference attacks. Extensive experiments on real-world graph datasets demonstrate the superior performance of APGE compared to the state-of-the-arts. Our source code can be found at.

8 March 2019 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
SJShihao Ji
Shihao Ji
NSNadathur Satish
Nadathur Satish
SLSheng Li
Sheng Li
PDPradeep K. Dubey
Pradeep K. Dubey

12 March 2024 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
HYHui Ye
Hui Ye
RSRajshekhar Sunderraman
Rajshekhar Sunderraman
SJShihao Ji
Shihao Ji
The eXtreme Multi-label text Classification (XMC) refers to training a classifier that assigns a text sample with relevant labels from an extremely large-scale label set (e.g., millions of labels). We propose MatchXML, an efficient textlabel matching framework for XMC. We observe that the label embeddings generated from the sparse Term Frequency-Inverse Document Frequency (TF–IDF) features have several limitations. We thus propose label2vec to effectively train the semantic dense label embeddings by the Skip-gram model. The dense label embeddings are then used to build a Hierarchical Label Tree by clustering. In fine-tuning the pre-trained encoder Transformer, we formulate the multi-label text classification as a text-label matching problem in a bipartite graph. We then extract the dense text representations from the fine-tuned Transformer. Besides the fine-tuned dense text embeddings, we also extract the static dense sentence embeddings from a pre-trained Sentence Transformer. Finally, a linear ranker is trained by utilizing the sparse TF–IDF features, the fine-tuned dense text representations, and static dense sentence features. Experimental results demonstrate that MatchXML achieves the state-of-the-art accuracies on five out of six datasets. As for the training speed, MatchXML outperforms the competing methods on all the six datasets. Our source code is publicly available at https://github.com/huiyegit/MatchXML .

1 October 2021
Verified
Conference Paper
Open access
XYXiulong Yang
Xiulong Yang
SJShihao Ji
Shihao Ji
Joint Energy-based Model (JEM) [12] is a recently proposed hybrid model that retains strong discriminative power of modern CNN classifiers, while generating samples rivaling the quality of GAN-based approaches. In this paper, we propose a variety of new training procedures and architecture features to improve JEM’s accuracy, training stability, and speed altogether. 1) We propose a proximal SGLD to generate samples in the proximity of samples from previous step, which improves the stability. 2) We further treat the approximate maximum likelihood learning of EBM as a multi-step differential game, and extend the YOPO framework [47] to cut out redundant calculations during backpropagation, which accelerates the training substantially. 3) Rather than initializing SGLD chain from random noise, we introduce a new informative initialization that samples from a distribution estimated from training data. 4) This informative initialization allows us to enable batch normalization in JEM, which further releases the power of modern CNN architectures for hybrid modeling. 1

28 March 2020
Verified
Book Chapter
Closed access
PDF file
XLXiang Li
Xiang Li
SJShihao Ji
Shihao Ji