1 code implementation • 10 Nov 2022 • Khang Tran, Phung Lai, NhatHai Phan, Issa Khalil, Yao Ma, Abdallah Khreishah, My Thai, Xintao Wu
Graph neural networks (GNNs) are susceptible to privacy inference attacks (PIAs), given their ability to learn joint representation from features and edges among nodes in graph data.
1 code implementation • 30 Aug 2022 • Harry Shomer, Wei Jin, Juanhui Li, Yao Ma, Jiliang Tang
It motivates us to design a framework that utilizes multiple aggregators to learn representations for hyper-relational facts: one from the perspective of the base triple and the other one from the perspective of the qualifiers.
no code implementations • 13 Aug 2022 • Hongliang Chi, Yao Ma
Graph contrastive learning (GCL) is a representative framework for self-supervised learning.
no code implementations • 5 Aug 2022 • Mehmet Fatih Ozkan, Yao Ma
With the proposed approach, trust-aware AVs generate explicable plans by optimizing both predefined plans and explicability of the plans in the car-following interactions with the following human driver.
no code implementations • 14 Jul 2022 • Mehmet Ozkan, Yao Ma
An inverse resource rational-based stochastic inverse reinforcement learning approach (IRR-SIRL) is proposed to learn a distribution of the planning horizon and cost function of the human driver with a given series of human demonstrations.
1 code implementation • 15 Jun 2022 • Wei Jin, Xiaorui Liu, Yao Ma, Charu Aggarwal, Jiliang Tang
In this paper, we propose a new perspective to look at the performance degradation of deep GNNs, i. e., feature overcorrelation.
1 code implementation • 21 May 2022 • Juanhui Li, Harry Shomer, Jiayuan Ding, Yiqi Wang, Yao Ma, Neil Shah, Jiliang Tang, Dawei Yin
This suggests a conflation of scoring function design, loss function design, and aggregation in prior work, with promising insights regarding the scalability of state-of-the-art KGC methods today, as well as careful attention to more suitable aggregation designs for KGC tasks tomorrow.
no code implementations • 26 Apr 2022 • Yao Ma, Junmin Wang
A Gaussian Process Regression model is further trained, validated, and tested under different traffic and vehicle conditions to predict fuel consumption based on drivers' personalized behaviors.
no code implementations • 3 Apr 2022 • Juanhui Li, Yao Ma, Wei Zeng, Suqi Cheng, Jiliang Tang, Shuaiqiang Wang, Dawei Yin
In other words, GE-BERT can capture both the semantic information and the users' search behavioral information of queries.
no code implementations • 27 Jan 2022 • Mehmet Fatih Ozkan, Yao Ma
The proposed DSMPC design integrates the stochastic driver behavior model of the human-driven leader truck with a distributed formation control design for the following automated trucks in the platoon.
no code implementations • 3 Dec 2021 • Mehmet Fatih Ozkan, Yao Ma
In the car-following scenarios, automated vehicles (AVs) usually plan motions without considering the impacts of their actions on the following human drivers.
1 code implementation • NeurIPS 2021 • Xiaorui Liu, Jiayuan Ding, Wei Jin, Han Xu, Yao Ma, Zitao Liu, Jiliang Tang
Graph neural networks (GNNs) have shown the power in graph representation learning for numerous tasks.
no code implementations • 29 Sep 2021 • Wei Jin, Xiaorui Liu, Yao Ma, Charu Aggarwal, Jiliang Tang
In this paper, we observe a new issue in deeper GNNs, i. e., feature overcorrelation, and perform a thorough study to deepen our understanding on this issue.
no code implementations • 28 Sep 2021 • Yao Ma, Shilin Zhao, Weixiao Wang, Yaoman Li, Irwin King
This survey provides a comprehensive overview of the multimodality-based meta-learning landscape in terms of the methodologies and applications.
no code implementations • 23 Aug 2021 • Zachary Grey, Susanna Mosleh, Jacob Rezac, Yao Ma, Jason Coder, Andrew Dienstfrey
We perform an exploratory analysis of coexistence behavior by approximating active subspaces to identify low-dimensional structure in the optimization criteria, i. e., few linear combinations of parameters for simultaneously maximizing LAA and Wi-Fi throughputs.
1 code implementation • 5 Jul 2021 • Xiaorui Liu, Wei Jin, Yao Ma, Yaxin Li, Hua Liu, Yiqi Wang, Ming Yan, Jiliang Tang
While many existing graph neural networks (GNNs) have been proven to perform $\ell_2$-based graph smoothing that enforces smoothness globally, in this work we aim to further enhance the local smoothness adaptivity of GNNs via $\ell_1$-based graph smoothing.
no code implementations • 1 Jul 2021 • Mehmet Fatih Ozkan, Abishek Joseph Rocque, Yao Ma
Compared to the deterministic baseline driver behavior model, the results reveal that the proposed stochastic driver behavior model can better replicate the driver's unique and rich driving strategies in a variety of traffic conditions.
no code implementations • 15 Jun 2021 • Mehmet Fatih Ozkan, Yao Ma
Simulation studies are conducted to investigate the fuel economy performance of the proposed control strategy and to validate the local and string stability of the platoon under a realistic traffic scenario.
no code implementations • ICLR 2022 • Yao Ma, Xiaorui Liu, Neil Shah, Jiliang Tang
We find that this claim is not quite true, and in fact, GCNs can achieve strong performance on heterophilous graphs under certain conditions.
1 code implementation • ICLR 2022 • Wei Jin, Xiaorui Liu, Xiangyu Zhao, Yao Ma, Neil Shah, Jiliang Tang
Then we propose the AutoSSL framework which can automatically search over combinations of various self-supervised tasks.
no code implementations • 10 May 2021 • Wei Jin, Xiaorui Liu, Yao Ma, Tyler Derr, Charu Aggarwal, Jiliang Tang
Graph neural networks (GNNs) have received tremendous attention due to their power in learning effective representations for graphs.
no code implementations • 26 Mar 2021 • Mehmet Ozkan, Yao Ma
The proposed PACC design plans the motion of the SAV by minimizing the learned unique cost function considering the short preview information of the preceding human-driven vehicle.
no code implementations • 2 Feb 2021 • Zachary J. Grey, Susanna Mosleh, Jacob D. Rezac, Yao Ma, Jason B. Coder, Andrew M. Dienstfrey
We perform an exploratory analysis of coexistence behavior by approximating active subspaces to identify low-dimensional structure in the optimization criteria, i. e., few linear combinations of parameters for simultaneously maximizing KPIs.
no code implementations • 1 Feb 2021 • Qu-Zhi Li, Yao Ma, Wen-Qi Niu, Yu-Fei Wang, Han-Qing Zheng
Extensive dynamical $N/D$ calculations are made in the study of $S_{11}$ channel low energy $\pi$N scatterings, based on various phenomenological model inputs of left cuts at tree level.
Nuclear Theory High Energy Physics - Phenomenology
1 code implementation • 19 Nov 2020 • Wei Jin, Tyler Derr, Yiqi Wang, Yao Ma, Zitao Liu, Jiliang Tang
Specifically, to balance information from graph structure and node features, we propose a feature similarity preserving aggregation which adaptively integrates graph structure and node features.
1 code implementation • 5 Oct 2020 • Yao Ma, Xiaorui Liu, Tong Zhao, Yozen Liu, Jiliang Tang, Neil Shah
In this work, we establish mathematically that the aggregation processes in a group of representative GNN models including GCN, GAT, PPNP, and APPNP can be regarded as (approximately) solving a graph denoising problem with a smoothness assumption.
no code implementations • 22 May 2020 • Yiqi Wang, Yao Ma, Wei Jin, Chaozhuo Li, Charu Aggarwal, Jiliang Tang
Therefore, in this paper, we aim to develop customized graph neural networks for graph classification.
3 code implementations • 20 May 2020 • Wei Jin, Yao Ma, Xiaorui Liu, Xianfeng Tang, Suhang Wang, Jiliang Tang
A natural idea to defend adversarial attacks is to clean the perturbed graph.
no code implementations • 17 May 2020 • Wenqi Fan, Tyler Derr, Xiangyu Zhao, Yao Ma, Hui Liu, Jian-Ping Wang, Jiliang Tang, Qing Li
In this work, we present our framework CopyAttack, which is a reinforcement learning based black-box attack method that harnesses real users from a source domain by copying their profiles into the target domain with the goal of promoting a subset of items.
4 code implementations • 17 Sep 2019 • Han Xu, Yao Ma, Haochen Liu, Debayan Deb, Hui Liu, Jiliang Tang, Anil K. Jain
In this survey, we review the state of the art algorithms for generating adversarial examples and the countermeasures against adversarial examples, for the three popular data types, i. e., images, graphs and text.
no code implementations • 16 Jul 2019 • Wenqi Fan, Yao Ma, Dawei Yin, Jian-Ping Wang, Jiliang Tang, Qing Li
Meanwhile, most of these models treat neighbors' information equally without considering the specific recommendations.
2 code implementations • ICLR 2020 • Zhiwei Wang, Yao Ma, Zitao Liu, Jiliang Tang
Recurrent Neural Networks have long been the dominating choice for sequence modeling.
Ranked #1 on
Music Modeling
on Nottingham
no code implementations • 10 Jun 2019 • Yao Ma, Suhang Wang, Tyler Derr, Lingfei Wu, Jiliang Tang
Graph Neural Networks (GNNs) have boosted the performance of many graph related tasks such as node classification and graph classification.
1 code implementation • 30 May 2019 • Wenqi Fan, Tyler Derr, Yao Ma, JianPing Wang, Jiliang Tang, Qing Li
Recent years have witnessed rapid developments on social recommendation techniques for improving the performance of recommender systems due to the growing influence of social networks to our daily life.
no code implementations • ICLR 2019 • Xiao Li, Yao Ma, Calin Belta
Skills learned through (deep) reinforcement learning often generalizes poorly across tasks and re-training is necessary when presented with a new task.
1 code implementation • 30 Apr 2019 • Yao Ma, Suhang Wang, Charu C. Aggarwal, Jiliang Tang
To apply graph neural networks for the graph classification task, approaches to generate the \textit{graph representation} from node representations are demanded.
Ranked #1 on
Graph Classification
on NC1
no code implementations • ICML 2018 • Yao Ma, Alex Olshevsky, Venkatesh Saligrama, Csaba Szepesvari
We consider worker skill estimation for the single-coin Dawid-Skene crowdsourcing model.
7 code implementations • 19 Feb 2019 • Wenqi Fan, Yao Ma, Qing Li, Yuan He, Eric Zhao, Jiliang Tang, Dawei Yin
These advantages of GNNs provide great potential to advance social recommendation since data in social recommender systems can be represented as user-user social graph and user-item graph; and learning latent factors of users and items is the key.
Ranked #3 on
Recommendation Systems
on Epinions
(using extra training data)
2 code implementations • 24 Oct 2018 • Yao Ma, Ziyi Guo, Zhaochun Ren, Eric Zhao, Jiliang Tang, Dawei Yin
Current graph neural network models cannot utilize the dynamic information in dynamic graphs.
no code implementations • 17 Sep 2018 • Xiao Li, Yao Ma, Calin Belta
Tasks with complex temporal structures and long horizons pose a challenge for reinforcement learning agents due to the difficulty in specifying the tasks in terms of reward functions as well as large variances in the learning signals.
1 code implementation • ICDM 2018 • Tyler Derr, Yao Ma, Jiliang Tang
However, since previous GCN models have primarily focused on unsigned networks (or graphs consisting of only positive links), it is unclear how they could be applied to signed networks due to the challenges presented by negative links.
Ranked #1 on
Link Sign Prediction
on Bitcoin-OTC
Social and Information Networks Physics and Society
no code implementations • 19 Aug 2018 • Zhiwei Wang, Yao Ma, Dawei Yin, Jiliang Tang
Recurrent Neural Networks (RNNs) have been proven to be effective in modeling sequential data and they have been applied to boost a variety of tasks such as document classification, speech recognition and machine translation.
no code implementations • 18 Aug 2018 • Yao Ma, Suhang Wang, Charu C. Aggarwal, Dawei Yin, Jiliang Tang
Convolutional neural networks (CNNs) leverage the great power in representation learning on regular grid data such as image and video.
Social and Information Networks
no code implementations • ICLR 2018 • Xiao Li, Yao Ma, Calin Belta
An obstacle that prevents the wide adoption of (deep) reinforcement learning (RL) in control systems is its need for a large number of interactions with the environment in order to master a skill.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
no code implementations • 31 Oct 2017 • Xiao Li, Yao Ma, Calin Belta
Skills learned through (deep) reinforcement learning often generalizes poorly across domains and re-training is necessary when presented with a new task.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
no code implementations • 27 Sep 2017 • Xiao Li, Yao Ma, Calin Belta
In this paper, we explore the use of temporal logic (TL) to specify tasks in reinforcement learning.
no code implementations • 20 Jun 2017 • Yao Ma, Alex Olshevsky, Venkatesh Saligrama, Csaba Szepesvari
We then formulate a weighted rank-one optimization problem to estimate skills based on observations on an irreducible, aperiodic interaction graph.
no code implementations • NeurIPS 2016 • Gang Niu, Marthinus Christoffel du Plessis, Tomoya Sakai, Yao Ma, Masashi Sugiyama
In PU learning, a binary classifier is trained from positive (P) and unlabeled (U) data without negative (N) data.
no code implementations • 15 Oct 2015 • Yao Ma, Hao Zhang, Masashi Sugiyama
The online Markov decision process (MDP) is a generalization of the classical Markov decision process that incorporates changing reward functions.
no code implementations • 21 Jul 2015 • Hao Zhang, Yao Ma, Masashi Sugiyama
We consider a task assignment problem in crowdsourcing, which is aimed at collecting as many reliable labels as possible within a limited budget.