Shifu: Deep Learning Based Advisor-advisee Relationship Mining in Scholarly Big Data

  title={Shifu: Deep Learning Based Advisor-advisee Relationship Mining in Scholarly Big Data},
  author={Wei Wang and Jiaying Liu and Feng Xia and Irwin King and Hanghang Tong},
  journal={Proceedings of the 26th International Conference on World Wide Web Companion},
  • Wei WangJiaying Liu Hanghang Tong
  • Published 3 April 2017
  • Computer Science
  • Proceedings of the 26th International Conference on World Wide Web Companion
Scholars in academia are involved in various social relationships such as advisor-advisee relationships. The analysis of such relationship can provide invaluable information for understanding the interactions among scholars as well as providing many researcher-specific applications such as advisor recommendation and academic rising star identification. However, in most cases, high quality advisor-advisee relationship dataset is unavailable. To address this problem, we propose Shifu, a deep… 

Figures and Tables from this paper

Shifu2: A Network Representation Learning Based Model for Advisor-Advisee Relationship Mining

A novel model based on Network Representation Learning (NRL), namely Shifu2, is proposed, which takes the collaboration network as input and the identified advisor-advisee relationship as output and considers not only the network structure but also the semantic information of nodes and edges.

Understanding the advisor–advisee relationship via scholarly data analysis

It is found that with the increase of advisors’ academic age, advisees’ performance experiences an initial growth, follows a sustaining stage, and finally ends up with a declining trend.

Attributed Collaboration Network Embedding for Academic Relationship Mining

This paper presents a meta-modelling architecture that automates the very labor-intensive and therefore time-heavy and expensive and expensive process of manually cataloging and cataloging scholarly data.

Network Representation Learning: From Traditional Feature Learning to Deep Learning

Network representation learning (NRL) is an effective graph analytics technique and promotes users to deeply understand the hidden characteristics of graph data. It has been successfully applied in

Exploring dynamic research interest and academic influence for scientific collaborator recommendation

This paper proposes a most Beneficial Collaborator Recommendation model called BCR, which learns on researchers’ publications and associates three academic features: topic distribution of research interest, interest variation with time andResearchers’ impact in collaborators network.

Mining latent academic social relationships by network fusion of multi-type data

A semi-supervised fusion framework for multiple networks (SFMN), using the gradient boosting decision tree algorithm to fuse the information of multiple networks into a single network, is proposed in this paper and implemented on Spark to improve the performance of large-scale social network analysis.

PePSI: Personalized Prediction of Scholars’ Impact in Heterogeneous Temporal Academic Networks

Experimental results on real data set demonstrate the effectiveness of PePSI in predicting top scholars and the overall impact of scholars with a rather short-term academic information as compared with the state-of-the-art prediction methods.

Strengthening Social Networks Analysis by Networks Fusion

A Semi-supervised Fusion framework for Multiple Network (SFMN), using gradient boosting decision tree algorithm (GBDT) to fuse the information of multi-source networks into a single network, which outperforms several state-of-the-art methods.



Mining advisor-advisee relationships from research publication networks

A time-constrained probabilistic factor graph model (TPFG), which takes a research publication network as input and models the advisor-advisee relationship mining problem using a jointly likelihood objective function is proposed and an efficient learning algorithm is designed to optimize the objective function.

Relationship Identification for Social Network Discovery

A supervised ranking approach is proposed to the challenge of relationship identification where the objective is to identify relevant communications that substantiate a given social relationship type and its performance on a manager-subordinate relationship identification task using the Enron email corpus is assessed.

Cross-domain collaboration recommendation

The Cross-domain Topic Learning (CTL) model is proposed, which consolidates the existing cross-domain collaborations through topic layers instead of at author layers, which alleviates the sparseness issue and outperforms baselines significantly on multiple recommendation metrics.

Traffic Flow Prediction With Big Data: A Deep Learning Approach

A novel deep-learning-based traffic flow prediction method is proposed, which considers the spatial and temporal correlations inherently and is applied for the first time that a deep architecture model is applied using autoencoders as building blocks to represent traffic flow features for prediction.

Collaboration Recommendation on Academic Social Networks

The architecture for such approach and the metrics involved in recommending collaborations on the context of academic Social Networks are introduced and an initial case study is presented to validate the approach.

Scholarly big data information extraction and integration in the CiteSeerχ digital library

This paper describes how CiteSeerχ aggregate data from multiple sources on the Web; store and manage data; process data as part of an automatic ingestion pipeline that includes automatic metadata and information extraction; perform document and citation clustering; perform entity linking and name disambiguation; and make data and source code available to enable research and collaboration.

Deep Learning

Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.

Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion

This work clearly establishes the value of using a denoising criterion as a tractable unsupervised objective to guide the learning of useful higher level representations.

A Fast Learning Algorithm for Deep Belief Nets

A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.

Quantifying the impact of weak, strong, and super ties in scientific careers

  • A. Petersen
  • Business
    Proceedings of the National Academy of Sciences
  • 2015
It is found that super ties contribute to above-average productivity and a 17% citation increase per publication, thus identifying these partnerships—the analog of life partners—as a major factor in science career development.