Search Results for author:
Found 21 papers, 3 papers with code
A Survey on Graph Representation Learning Methods
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.
Extending Isolation Forest for Anomaly Detection in Big Data via K-Means
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.
Affective and Contextual Embedding for Sarcasm Detection
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.
A Comprehensive Analysis of Preprocessing for Word Representation Learning in Affective Tasks
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.
Adaptive Momentum Coefficient for Neural Network Optimization
We propose a novel and efficient momentum-based first-order algorithm for optimizing neural networks which uses an adaptive coefficient for the momentum term.
Elastic Bulk Synchronous Parallel Model for Distributed Deep Learning
To ameliorate this shortcoming of classic BSP, we propose ELASTICBSP a model that aims to relax its strict synchronization requirement.
Learning to Determine the Quality of News Headlines
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of the calculated quality indicators to train our proposed deep learning model which can predict the quality of unpublished news headlines.
Dynamic Graph Embedding via LSTM History Tracking
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.
Dynamic Joint Variational Graph Autoencoders
Learning network representations is a fundamental task for many graph applications such as link prediction, node classification, graph clustering, and graph visualization.
Dynamic Stale Synchronous Parallel Distributed Training for Deep Learning
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.
Content-based Dwell Time Engagement Prediction Model for News Articles
The article dwell time (i. e., expected time that users spend on an article) is among the most important factors showing the article engagement.
dynnode2vec: Scalable Dynamic Network Embedding
Node2vec is a random walk based embedding method for static networks.
Learning Emotion-enriched Word Representations
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{''}.
Using Neural Network for Identifying Clickbaits in Online News Media
Online news media sometimes use misleading headlines to lure users to open the news article.
Spontaneous Symmetry Breaking in Deep Neural Networks
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.
Decoupling the Layers in Residual Networks
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.
Spontaneous Symmetry Breaking in Neural Networks
We propose a framework to understand the unprecedented performance and robustness of deep neural networks using field theory.
Optimization assisted MCMC
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.
Selective Co-occurrences for Word-Emotion Association
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.
