no code implementations • 4 Apr 2022 • Shima Khoshraftar, Aijun An
This is especially important because the quality of the graph representation vectors will affect the performance of these vectors in downstream tasks such as node classification, link prediction and anomaly detection.
no code implementations • 27 Apr 2021 • Md Tahmid Rahman Laskar, Jimmy Huang, Vladan Smetana, Chris Stewart, Kees Pouw, Aijun An, Stephen Chan, Lei Liu
Moreover, we evaluate our proposed model on the live streaming data and find that our proposed system can be used for real-time anomaly detection in the industrial setup.
1 code implementation • COLING 2020 • Nastaran Babanejad, Heidar Davoudi, Aijun An, Manos Papagelis
To the best of our knowledge, this is the first attempt to directly alter BERT{'}s architecture and train it from scratch to build a sarcasm classifier.
no code implementations • ACL 2020 • Nastaran Babanejad, Ameeta Agrawal, Aijun An, Manos Papagelis
Affective tasks such as sentiment analysis, emotion classification, and sarcasm detection have been popular in recent years due to an abundance of user-generated data, accurate computational linguistic models, and a broad range of relevant applications in various domains.
1 code implementation • 4 Jun 2020 • Zana Rashidi, Kasra Ahmadi K. A., Aijun An, Xiaogang Wang
We propose a novel and efficient momentum-based first-order algorithm for optimizing neural networks which uses an adaptive coefficient for the momentum term.
no code implementations • 6 Jan 2020 • Xing Zhao, Manos Papagelis, Aijun An, Bao Xin Chen, Junfeng Liu, Yonggang Hu
To ameliorate this shortcoming of classic BSP, we propose ELASTICBSP a model that aims to relax its strict synchronization requirement.
no code implementations • 26 Nov 2019 • Amin Omidvar, Hossein Poormodheji, Aijun An, Gordon Edall
Then, we use soft target distribution of the calculated quality indicators to train our proposed deep learning model which can predict the quality of unpublished news headlines.
no code implementations • 5 Nov 2019 • Shima Khoshraftar, Sedigheh Mahdavi, Aijun An, Yonggang Hu, Junfeng Liu
To handle large dynamic networks in downstream applications such as link prediction and anomaly detection, it is essential for such networks to be transferred into a low dimensional space.
no code implementations • 4 Oct 2019 • Sedigheh Mahdavi, Shima Khoshraftar, Aijun An
Learning network representations is a fundamental task for many graph applications such as link prediction, node classification, graph clustering, and graph visualization.
no code implementations • 16 Aug 2019 • Xing Zhao, Aijun An, Junfeng Liu, Bao Xin Chen
In this paper, we present a distributed paradigm on the parameter server framework called Dynamic Stale Synchronous Parallel (DSSP) which improves the state-of-the-art Stale Synchronous Parallel (SSP) paradigm by dynamically determining the staleness threshold at the run time.
no code implementations • NAACL 2019 • Heidar Davoudi, Aijun An, Gordon Edall
The article dwell time (i. e., expected time that users spend on an article) is among the most important factors showing the article engagement.
no code implementations • 6 Dec 2018 • Sedigheh Mahdavi, Shima Khoshraftar, Aijun An
Node2vec is a random walk based embedding method for static networks.
no code implementations • COLING 2018 • Ameeta Agrawal, Aijun An, Manos Papagelis
As a consequence, emotionally dissimilar words, such as {``}happy{''} and {``}sad{''} occurring in similar contexts would purport more similar meaning than emotionally similar words, such as {``}happy{''} and {``}joy{''}.
2 code implementations • 20 Jun 2018 • Amin Omidvar, Hui Jiang, Aijun An
Online news media sometimes use misleading headlines to lure users to open the news article.
no code implementations • ICLR 2018 • Ricky Fok, Aijun An, Zana Rashidi, Xiaogang Wang
We propose a Warped Residual Network (WarpNet) using a parallelizable warp operator for forward and backward propagation to distant layers that trains faster than the original residual neural network.
no code implementations • ICLR 2018 • Ricky Fok, Aijun An, Xiaogang Wang
In the layer decoupling limit applicable to residual networks (He et al., 2015), we show that the remnant symmetries that survive the non-linear layers are spontaneously broken based on empirical results.
no code implementations • 17 Oct 2017 • Ricky Fok, Aijun An, Xiaogang Wang
We propose a framework to understand the unprecedented performance and robustness of deep neural networks using field theory.
no code implementations • 9 Sep 2017 • Ricky Fok, Aijun An, Xiaogang Wang
The global optimization method first reduces a high dimensional search to an one dimensional geodesic to find a starting point close to a local mode.
no code implementations • COLING 2016 • Ameeta Agrawal, Aijun An
Emotion classification from text typically requires some degree of word-emotion association, either gathered from pre-existing emotion lexicons or calculated using some measure of semantic relatedness.