Paper

These are all the papers I wrote on some topics. Including published conference/jpurnal papers and unpublished project papers.

Recurrent Attention Walk for Semi-supervised Classification

2019-10-24 16:12:04 | Uchenna Akujuobi, Qiannan Zhang, Han Yufei, Xiangliang Zhang􏰃

ABSTRACT In this paper, we study the graph-based semi-supervised learning for classifying nodes in attributed networks, where the nodes and edges possess content information. Recent approaches like graph convolution networks and attention...

Collaborative Graph Walk for Semi-supervised Multi-Label Node Classification

2019-10-24 16:13:04 | Uchenna Akujuobi, Han Yufei, Qiannan Zhang, Xiangliang Zhang

ABSTRACT In this work, we study semi-supervised multi-label node classification problem in attributed graphs. Classic solutions to multi-label node classification follow two steps, first learn node embedding and then build a node classifier...

Mining top-k Popular Datasets via a Deep Generative Model

2019-10-23 18:09:46 | Akujuobi Uchenna, Ke Sun, and Xiangliang Zhang

Abstract Finding popular datasets to work on is essential for data-driven research domains. In this paper, we focus on the problem of extracting top-k popular datasets that have been used in data mining, machine learning, and artificial...

Delve: A Dataset-Driven Scholarly Search and Analysis System

2019-10-23 18:10:16 | Akujuobi Uchenna, and Xiangliang Zhang

ABSTRACT Research and experimentation in various scientific fields are based on the observation, analysis and benchmarking on datasets. The advancement of research and development has thus, strengthened the importance of dataset access. However,...

Delve: A data set retrieval and document analysis system

2019-10-23 18:10:37 | Akujuobi Uchenna, and Xiangliang Zhang

ABSTRACT Academic search engines (e.g., Google scholar or Microsoft academic) provide a medium for retrieving various information on scholarly documents. However, most of these popular scholarly search engines overlook the area of data set...

Real-Time Crime Prediction For Efficient Response

2017-03-11 05:18:43 | Uchenna

Problem: Sometimes, crime victims don’t get the opportunity or time to make that 911 call to call for help. Sometimes it’s very risky to do so at that particular moment thereby, leading to them having less chances of getting...

Efficiency And Performance Of Search Algorithms On Real Applications

2017-03-11 05:17:25 | Uchenna

Okwe is a popular game played by the Igbo people of south eastern Nigeria. This game is a member of the big Mancala family game. This work presents an artificial intelligence (AI) designed to play Okwe efficiently. This work also tries to show the...

Paper Report On Phase Reconciliation For Contended In-Memory Transactions

2017-03-11 05:19:28 | Uchenna

To gain more performance and make maximum use of the cores, a process should execute in parallel which should result in increased speed in process execution, resources used to the maximum capacity, better performance, etc. This would have been...