no code implementations • 9 Dec 2023 • Shukai Duan, Nikos Kanakaris, Xiongye Xiao, Heng Ping, Chenyu Zhou, Nesreen K. Ahmed, Guixiang Ma, Mihai Capota, Theodore L. Willke, Shahin Nazarian, Paul Bogdan
We compare our framework with existing state-of-the-art models and show that it is more efficient with respect to speed and computational usage, as a result of the decrement in training steps and its applicability to models with fewer parameters.
no code implementations • 8 Jul 2023 • Chao Chen, Chenghua Guo, Guixiang Ma, Ming Zeng, Xi Zhang, Sihong Xie
Robust explanations of machine learning models are critical to establish human trust in the models.
no code implementations • 28 Dec 2022 • Chao Chen, Chenghua Guo, Guixiang Ma, Ming Zeng, Xi Zhang, Sihong Xie
Robust explanations of machine learning models are critical to establishing human trust in the models.
1 code implementation • 25 Oct 2022 • Zehua Zhang, Shilin Sun, Guixiang Ma, Caiming Zhong
Link prediction tasks focus on predicting possible future connections.
no code implementations • 22 Sep 2022 • Guixiang Ma, Vy A. Vo, Theodore Willke, Nesreen K. Ahmed
We provide a comprehensive review of the existing literature on memory-augmented GNNs.
no code implementations • 14 Jul 2022 • Haoteng Tang, Guixiang Ma, Lei Guo, Xiyao Fu, Heng Huang, Liang Zhang
Here, we propose an interpretable hierarchical signed graph representation learning model to extract graph-level representations from brain functional networks, which can be used for different prediction tasks.
no code implementations • 25 Apr 2022 • Yao Xiao, Guixiang Ma, Nesreen K. Ahmed, Mihai Capota, Theodore Willke, Shahin Nazarian, Paul Bogdan
To enable heterogeneous computing systems with autonomous programming and optimization capabilities, we propose a unified, end-to-end, programmable graph representation learning (PGL) framework that is capable of mining the complexity of high-level programs down to the universal intermediate representation, extracting the specific computational patterns and predicting which code segments would run best on a specific core in heterogeneous hardware platforms.
1 code implementation • AAAI 2022 • Mengzhu Sun, Xi Zhang, Jiaqi Zheng, Guixiang Ma
Moreover, the dynamics of knowledge information associated with the comments are not involved, either.
no code implementations • 15 Sep 2021 • Chao Chen, Yifan Shen, Guixiang Ma, Xiangnan Kong, Srinivas Rangarajan, Xi Zhang, Sihong Xie
Learning to compare two objects are essential in applications, such as digital forensics, face recognition, and brain network analysis, especially when labeled data is scarce and imbalanced.
no code implementations • 9 Aug 2021 • Haozhe Jia, Haoteng Tang, Guixiang Ma, Weidong Cai, Heng Huang, Liang Zhan, Yong Xia
In the PSGR module, a graph is first constructed by projecting each pixel on a node based on the features produced by the segmentation backbone, and then converted into a sparsely-connected graph by keeping only K strongest connections to each uncertain pixel.
no code implementations • 14 Apr 2021 • Vasimuddin Md, Sanchit Misra, Guixiang Ma, Ramanarayan Mohanty, Evangelos Georganas, Alexander Heinecke, Dhiraj Kalamkar, Nesreen K. Ahmed, Sasikanth Avancha
Full-batch training on Graph Neural Networks (GNN) to learn the structure of large graphs is a critical problem that needs to scale to hundreds of compute nodes to be feasible.
no code implementations • 10 Dec 2020 • Haoteng Tang, Guixiang Ma, Lifang He, Heng Huang, Liang Zhan
In this paper, we propose a new interpretable graph pooling framework - CommPOOL, that can capture and preserve the hierarchical community structure of graphs in the graph representation learning process.
no code implementations • NeurIPS Workshop LMCA 2020 • Aaron Zweig, Nesreen Ahmed, Theodore L. Willke, Guixiang Ma
The application of deep reinforcement learning (RL) to graph learning and meta-learning admits challenges from both topics.
no code implementations • 9 Oct 2020 • Guixiang Ma, Yao Xiao, Theodore L. Willke, Nesreen K. Ahmed, Shahin Nazarian, Paul Bogdan
High-level applications, such as machine learning, are evolving from simple models based on multilayer perceptrons for simple image recognition to much deeper and more complex neural networks for self-driving vehicle control systems. The rapid increase in the consumption of memory and computational resources by these models demands the use of multi-core parallel systems to scale the execution of the complex emerging applications that depend on them.
1 code implementation • 10 Jun 2020 • Yingtong Dou, Guixiang Ma, Philip S. Yu, Sihong Xie
We experiment on three large review datasets using various state-of-the-art spamming and detection strategies and show that the optimization algorithm can reliably find an equilibrial detector that can robustly and effectively prevent spammers with any mixed spamming strategies from attaining their practical goal.
no code implementations • 23 May 2020 • Haoteng Tang, Guixiang Ma, Yurong Chen, Lei Guo, Wei Wang, Bo Zeng, Liang Zhan
However, most of the existing work in this area focus on the GNNs for node-level tasks, while little work has been done to study the robustness of the GNNs for the graph classification task.
no code implementations • 25 Dec 2019 • Guixiang Ma, Nesreen K. Ahmed, Theodore L. Willke, Philip S. Yu
In many domains where data are represented as graphs, learning a similarity metric among graphs is considered a key problem, which can further facilitate various learning tasks, such as classification, clustering, and similarity search.
no code implementations • 8 Nov 2019 • Jiahao Liu, Guixiang Ma, Fei Jiang, Chun-Ta Lu, Philip S. Yu, Ann B. Ragin
Specifically, we use graph convolutions to learn the structural and functional joint embedding, where the graph structure is defined with structural connectivity and node features are from the functional connectivity.
no code implementations • 9 Nov 2018 • Shuaijun Ge, Guixiang Ma, Sihong Xie, Philip S. Yu
In terms of security, DETER is versatile enough to be vaccinated against diverse and unexpected evasions, is agnostic about evasion strategy and can be released without privacy concern.
no code implementations • 2 Nov 2018 • Guixiang Ma, Nesreen K. Ahmed, Ted Willke, Dipanjan Sengupta, Michael W. Cole, Nicholas B. Turk-Browne, Philip S. Yu
We propose an end-to-end similarity learning framework called Higher-order Siamese GCN for multi-subject fMRI data analysis.
no code implementations • 12 Sep 2017 • Guixiang Ma, Chun-Ta Lu, Lifang He, Philip S. Yu, Ann B. Ragin
Specifically, we propose an auto-weighted framework of Multi-view Graph Embedding with Hub Detection (MVGE-HD) for brain network analysis.
no code implementations • ICML 2017 • Lifang He, Chun-Ta Lu, Guixiang Ma, Shen Wang, Linlin Shen, Philip S. Yu, Ann B. Ragin
In the context of supervised tensor learning, preserving the structural information and exploiting the discriminative nonlinear relationships of tensor data are crucial for improving the performance of learning tasks.