OAG: Linking Entities Across Large-Scale Heterogeneous Knowledge Graphs

Zhang, Fanjin; Liu, Xiao; Tang, Jie; Dong, Yuxiao; Yao, Peiran; Zhang, Jie; Gu, Xueping; Wang, Yan; Kharlamov, Evgeny; Shao, Bin; Li, Rui; Wang, Kuansan

doi:10.1109/tkde.2022.3222168

Cited by 10 publications

(8 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• SciBERT [2] 1 is a scientific PLM trained on 1.14M scientific papers from Semantic Scholar [1] using masked language modeling and next sentence prediction tasks. • OAG-BERT [24] 2 is a scientific PLM trained on 120M scientific papers from the Open Academic Graph [61]. It proposes heterogeneous entity type embedding, span-aware entity masking, and Table 2: P@𝑘 and NDCG@𝑘 scores of compared methods on MAG-CS and PubMed.…”

Section: Experiments 41 Setupmentioning

confidence: 99%

Weakly Supervised Multi-Label Classification of Full-Text Scientific Papers

Zhang

Jin

Chen

et al. 2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Instead of relying on human-annotated training samples to build a classifier, weakly supervised scientific paper classification aims to classify papers only using category descriptions (e.g., category names, category-indicative keywords). Existing studies on weakly supervised paper classification are less concerned with two challenges: (1) Papers should be classified into not only coarse-grained research topics but also fine-grained themes, and potentially into multiple themes, given a large and fine-grained label space; and(2) full text should be utilized to complement the paper title and abstract for classification. Moreover, instead of viewing the entire paper as a long linear sequence, one should exploit the structural information such as citation links across papers and the hierarchy of sections and paragraphs in each paper. To tackle these challenges, in this study, we propose FuTex, a framework that uses the cross-paper network structure and the in-paper hierarchy structure to classify full-text scientific papers under weak supervision. A network-aware contrastive fine-tuning module and a hierarchyaware aggregation module are designed to leverage the two types of structural signals, respectively. Experiments on two benchmark datasets demonstrate that FuTex significantly outperforms competitive baselines and is on par with fully supervised classifiers that use 1,000 to 60,000 ground-truth training samples. CCS CONCEPTS• Information systems → Data mining; • Computing methodologies → Classification and regression trees.

show abstract

Section: Experiments 41 Setupmentioning

confidence: 99%

Weakly Supervised Multi-Label Classification of Full-Text Scientific Papers

Zhang

Jin

Chen

et al. 2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

show abstract

“…These references can be consequently aligned to paper entities with rich meta-information (e.g. abstract, fieldof-study (FOS)) in the Open Academic Graph (OAG) (Zhang et al, 2019), the largest publicly available academic entity graph to date. We collect questions from two influential websites: Stack Exchange 2 in English, and Zhihu 3 in Chinese.…”

Section: Cross-domain and Cross-topic Generalizabilitymentioning

confidence: 99%

“…We collect questions from two influential websites: Stack Exchange 2 in English, and Zhihu 3 in Chinese. On top of the collected pairs of questions and paper titles, we align them to OAG (Zhang et al, 2019;Wang et al, 2020a;Tang et al, 2008) paper ids via public API 4 . In terms of topics, disciplines from Stack Exchange and tags from Zhihu naturally serve as fine-grained topics attached to 3) which consists of 17,948 unique queries from 22 scientific disciplines and 87 fine-grained topics.…”

Section: Cross-domain and Cross-topic Generalizabilitymentioning

confidence: 99%

Parameter-Efficient Prompt Tuning Makes Generalized and Calibrated Neural Text Retrievers

Tam,

Liu,

et al. 2023

Findings of the Association for Computational Linguistics: EMNLP 2023

View full text Add to dashboard Cite

Prompt tuning attempts to update few taskspecific parameters in pre-trained models. It has achieved comparable performance to finetuning of the full parameter set on both language understanding and generation tasks. In this work, we study the problem of prompt tuning for neural text retrievers. We introduce parameter-efficient prompt tuning for text retrieval across in-domain, cross-domain, and cross-topic settings. Through an extensive analysis, we show that the strategy can mitigate the two issues-parameter-inefficiency and weak generalizability-faced by fine-tuning based retrieval methods. Notably, it can significantly improve the out-of-domain zero-shot generalization of the retrieval models. By updating only 0.1% of the model parameters, the prompt tuning strategy can help retrieval models achieve better generalization performance than traditional methods in which all parameters are updated. Finally, to facilitate research on retrievers' cross-topic generalizability, we curate and release an academic retrieval dataset with 18K query-results pairs in 87 topics, making it the largest topic-specific one to date. 1

show abstract

“…In this paper, we aim at verifying this observation that the conferences and research fields in the computer science field have become similar quantitatively and qualitatively, and we take 17 conferences in 6 research fields as an example. The Open Academic Graph [13] (OAG) provides a large-scale graph network that contains more than 178 million nodes and 2.236 billion edges, spanning from 1900 to 2018. However, OAG lacks of the recent conferences from 2019 to 2020, and we complement these conferences to original OAG as OAGv3.…”

Section: Introductionmentioning

confidence: 99%

A Trend of AI Conference Convergence in Similarity: An Empirical Study Through Trans-Temporal Heterogeneous Graph

Gao

Zhang

Chen

et al. 2023

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Publishing the research works on academic publications is an important part of the scientific process. Since the development of computer science research is very fast, researchers tend to publish the research works in a fast way, such as conferences whose review processes are faster than the journals. In the past decades, one conference usually focuses on a specific research field and the topic or method overlap between conferences is low. We have noticed that, in recent years, some topics or methods which were once studied in a small number of specific research fields have become popular in many other fields. Naturally, we come up with two research questions: (1) Do the conferences indeed become similar? and (2) How do conferences become similar? In this paper, we first use a trans-temporal heterogeneous graph network to model academic conferences in recent 20 years. Due to the large number of conferences, we categorize these conferences into 6 research fields for brevity. Then, we first quantitatively and qualitatively assess "Do the research fields become similar?" and then focus on exploring "How do research fields become similar?". From the result, we find the reason for the research fields in computer science become similar is that AI becomes pervasive and researchers tend to apply the machine learning methods to different application fields. Since the methods become universal between different research fields, researchers should pay more attention to advanced information in other fields to motivate more interdisciplinary works. To assist the researchers to explore related interdisciplinary advanced information, it is crucial to measure the cross-field impact of papers using the citation information and recommend the paper which has a high cross-field impact on the related researchers. As for the newly published papers which do not have any citations, we also propose a cross-field impact prediction model to recommend the cutting-edge research works to related researchers accurately. Experiments conducted on real-world datasets verify the effectiveness of the proposed method.

show abstract

OAG: Linking Entities Across Large-Scale Heterogeneous Knowledge Graphs

Cited by 10 publications

References 61 publications

Weakly Supervised Multi-Label Classification of Full-Text Scientific Papers

Weakly Supervised Multi-Label Classification of Full-Text Scientific Papers

Parameter-Efficient Prompt Tuning Makes Generalized and Calibrated Neural Text Retrievers

A Trend of AI Conference Convergence in Similarity: An Empirical Study Through Trans-Temporal Heterogeneous Graph

Contact Info

Product

Resources

About