Huobin Tan

Dr. Huobin Tan


Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 January 2021 in IEEE Access
Verified
Journal Article
Open access
XLXiyang Liu
Xiyang Liu
HTHuobin Tan
Huobin Tan
QCQinghong Chen
Qinghong Chen
GLGuangyan Lin
Guangyan Lin
Knowledge graph completion (KGC) is the task of predicting missing links based on known triples for knowledge graphs. Several recent works suggest that Graph Neural Networks (GNN) that exploit graph structures achieve promising performance on KGC. These models learn information called messages from neighboring entities and relations and then aggregate messages to update central entity representations. The drawback of existing GNN based models lies in that they tend to treat relations equally and learn fixed network parameters, overlooking the distinction of each relational information. In this work, we propose a R elation A ware G raph AT tention network (RAGAT) that constructs separate message functions for different relations, which aims at exploiting the heterogeneous characteristics of knowledge graphs. Specifically, we introduce relation specific parameters to augment the expressive capability of message functions, which enables the model to extract relational information in parameter space. To validate the effect of relation aware mechanism, RAGAT is implemented with a variety of relation aware message functions. Experiments show RAGAT outperforms state-of-the-art link prediction baselines on standard FB15k-237 and WN18RR datasets.


9 November 2018
Verified
Book Chapter
Open access
PDF file
LJLi Ji
Li Ji
GLGuangyan Lin
Guangyan Lin
HTHuobin Tan
Huobin Tan
Collaborative filtering methods are widely used for recommender systems. However the performance degrades significantly because of highly sparse rating information in practical situations. Recently many hybrid models incorporating content information have been proposed to alleviate data sparsity. This paper first proposes the collaborative variational ranking model (CVRank) that combines variational autoencoder with pairwise ranking based collaborative filtering. The model learns latent factors of users and items from both rating and content information, and makes recommendation by calculating dot products between users and items. CVRank is suitable for other deep learning models, and can be easily extended to other multimedia other than text. Then this paper sums up similar models as neural collaborative filtering and presents a generic optimization criterion for them. Experiments show that CVRank achieves robust performance under different sparsity level, and neural collaborative filtering methods can gain greater recommendation accuracy improvement compared with pure collaborative filtering when the training data is sparser.

18 November 2023
Verified
Conference Paper
Open access
BZBotong Zhu
Botong Zhu
HTHuobin Tan
Huobin Tan
In this paper, we present a model named VuLASTE, treating vulnerability detection as a specialized text classification task. To address the vocabulary explosion problem, VuLASTE utilizes a byte-level BPE algorithm from natural language processing. Within VuLASTE, we introduce a novel AST path embedding to represent source code nesting information. Additionally, we employ a combination of global and dilated window attention from Longformer to extract long sequence semantics from source code. To tackle the issue of data imbalance, a common challenge in vulnerability detection datasets, we employ focal loss as a loss function. This ensures that the model prioritizes poorly classified cases during training. To evaluate our model's performance on real-world source code, we construct a cross-language and multi-repository vulnerability dataset from the Github Security Advisory Database. VuLASTE achieves top 50, top 100, top 200, and top 500 hits of 29, 51, 86, and 228, respectively, surpassing state-of-the-art researches.

5 November 2019 in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
Verified
Journal Article
Closed access
PDF file
HTHuobin Tan
Huobin Tan
YTYongfeng Tian
Yongfeng Tian
LWLinfeng Wang
Linfeng Wang
GLGuangyan Lin
Guangyan Lin
The name disambiguation task is designed to solve the name ambiguity problem of documents of multiple persons who have the same name with one another. The task aims to partition all the publications belonging to multiple person with the same name and realize that each decomposed partition is composed of publications of a unique person. Many works on name disambiguation task have a common feature that clustering method is usually used in the last step. The paper presents a complementary study to these works from another point of view. Based on the idea that documents with strong association relationships are likely to belong to the same author, this paper proposes a method of discovering meta clusters by graph partition with a heuristic rule to improve these clustering-based works. Specially, different from these works, this work uses clustering ensemble method instead of clustering method in the last step. Experimental results on a real-life dataset show that the improved method has satisfactory performance compared with the clustering-based baseline method.