Genghong Zhao

Dr. Genghong Zhao


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
6 December 2024 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
XZXuanyi Zhang
Xuanyi Zhang
GZGenghong Zhao
Genghong Zhao
YRYi Ren
Yi Ren
WWWeiguang Wang
Weiguang Wang
WCWei Cai
Wei Cai
JLJiren Liu
Jiren Liu

29 April 2023
Verified
Journal Article
Closed access
LLLinh Le
Linh Le
GZGuido Zuccon
Guido Zuccon
GDGianluca Demartini
Gianluca Demartini
GZGenghong Zhao
Genghong Zhao
XZXia Zhang
Xia Zhang

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
LLLinh Le
Linh Le
GZGenghong Zhao
Genghong Zhao
XZXia Zhang
Xia Zhang
GZGuido Zuccon
Guido Zuccon
GDGianluca Demartini
Gianluca Demartini
In the machine learning field, the challenge of effectively learning with limited data has become increasingly crucial. Active Learning (AL) algorithms play a significant role in this by enhancing model performance. We introduce a novel AL algorithm, termed Co-learning (CoLAL), designed to select the most diverse and representative samples within a training dataset. This approach utilizes noisy labels and predictions made by the primary model on unlabeled data. By leveraging a probabilistic graphical model, we combine two multi-class classifiers into a binary one. This classifier determines if both the main and the peer models agree on a prediction. If they do, the unlabeled sample is assumed to be easy to classify and is thus not beneficial to increase the target model's performance. We prioritize data that represents the unlabeled set without overlapping decision boundaries. The discrepancies between these boundaries can be estimated by the probability that two models result in the same prediction. Through theoretical analysis and experimental validation, we reveal that the integration of noisy labels into the peer model effectively identifies target model's potential inaccuracies. We evaluated the CoLAL method across seven benchmark datasets: four text datasets (AGNews, DBPedia, PubMed, SST-2) and text-based state-of-the-art (SOTA) baselines, and three image datasets (CIFAR100, MNIST, OpenML-155) and computer vision SOTA baselines. The results show that our CoLAL method significantly outperforms existing SOTA in text-based AL, and is competitive with SOTA image-based AL techniques.

7 March 2025 in arXiv
Verified
Preprint
Open access
PDF file
LLLinh Le
Linh Le
GZGuido Zuccon
Guido Zuccon
GDGianluca Demartini
Gianluca Demartini
GZGenghong Zhao
Genghong Zhao
XZXia Zhang
Xia Zhang
Previous work on clinical relation extraction from free-text sentences leveraged information about semantic types from clinical knowledge bases as a part of entity representations. In this paper, we exploit additional evidence by also making use of domain-specific semantic type dependencies. We encode the relation between a span of tokens matching a Unified Medical Language System (UMLS) concept and other tokens in the sentence. We implement our method and compare against different named entity recognition (NER) architectures (i.e., BiLSTM-CRF and BiLSTM-GCN-CRF) using different pre-trained clinical embeddings (i.e., BERT, BioBERT, UMLSBert). Our experimental results on clinical datasets show that in some cases NER effectiveness can be significantly improved by making use of domain-specific semantic type dependencies. Our work is also the first study generating a matrix encoding to make use of more than three dependencies in one pass for the NER task.

29 November 2022 in arXiv
Verified
Preprint
Open access
PDF file
BLBing Liu
Bing Liu
HSHarrisen Scells
Harrisen Scells
WHWen Hua
Wen Hua
GZGuido Zuccon
Guido Zuccon
GZGenghong Zhao
Genghong Zhao
XZXia Zhang
Xia Zhang
Entity Alignment (EA) aims to find equivalent entities between two Knowledge Graphs (KGs). While numerous neural EA models have been devised, they are mainly learned using labelled data only. In this work, we argue that different entities within one KG should have compatible counterparts in the other KG due to the potential dependencies among the entities. Making compatible predictions thus should be one of the goals of training an EA model along with fitting the labelled data: this aspect however is neglected in current methods. To power neural EA models with compatibility, we devise a training framework by addressing three problems: (1) how to measure the compatibility of an EA model; (2) how to inject the property of being compatible into an EA model; (3) how to optimise parameters of the compatibility model. Extensive experiments on widely-used datasets demonstrate the advantages of integrating compatibility within EA models. In fact, state-of-the-art neural EA models trained within our framework using just 5\% of the labelled data can achieve comparable effectiveness with supervised training using 20\% of the labelled data.