More Like this

1. BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models

   Hao Shibo, Tan Bowen (July 2023, Findings of the Association for Computational Linguistics: ACL 2023)

   It is crucial to automatically construct knowledge graphs (KGs) of diverse new relations to support knowledge discovery and broad applications. Previous KG construction methods, based on either crowdsourcing or text mining, are often limited to a small predefined set of relations due to manual cost or restrictions in text corpus. Recent research proposed to use pretrained language models (LMs) as implicit knowledge bases that accept knowledge queries with prompts. Yet, the implicit knowledge lacks many desirable properties of a full-scale symbolic KG, such as easy access, navigation, editing, and quality assurance. In this paper, we propose a new approach of harvesting massive KGs of arbitrary relations from pretrained LMs. With minimal input of a relation definition (a prompt and a few shot of example entity pairs), the approach efficiently searches in the vast entity pair space to extract diverse accurate knowledge of the desired relation. We develop an effective search-and-rescore mechanism for improved efficiency and accuracy. We deploy the approach to harvest KGs of over 400 new relations, from LMs of varying capacities such as RoBERTaNet. Extensive human and automatic evaluations show our approach manages to extract diverse accurate knowledge, including tuples of complex relations (e.g., “A is capable of but not good at B”). The resulting KGs as a symbolic interpretation of the source LMs also reveal new insights into the LMs’ knowledge capacities. 

   more » « less
2. Few-Shot Knowledge Graph Completion

   https://doi.org/10.1609/aaai.v34i03.5698  

   Zhang, Chuxu; Yao, Huaxiu; Huang, Chao; Jiang, Meng; Li, Zhenhui; Chawla, Nitesh V. (June 2020, Proceedings of the AAAI Conference on Artificial Intelligence)

   Knowledge graphs (KGs) serve as useful resources for various natural language processing applications. Previous KG completion approaches require a large number of training instances (i.e., head-tail entity pairs) for every relation. The real case is that for most of the relations, very few entity pairs are available. Existing work of one-shot learning limits method generalizability for few-shot scenarios and does not fully use the supervisory information; however, few-shot KG completion has not been well studied yet. In this work, we propose a novel few-shot relation learning model (FSRL) that aims at discovering facts of new relations with few-shot references. FSRL can effectively capture knowledge from heterogeneous graph structure, aggregate representations of few-shot references, and match similar entity pairs of reference set for every relation. Extensive experiments on two public datasets demonstrate that FSRL outperforms the state-of-the-art. 

   more » « less
3. REFORM: Error-Aware Few-Shot Knowledge Graph Completion

   https://doi.org/10.1145/3459637.3482470  

   Wang, Song; Huang, Xiao; Chen, Chen; Wu, Liang; Li, Jundong (October 2021, Proceedings of the 30th ACM International Conference on Information & Knowledge Management)

   Knowledge graphs (KGs) are of great importance in various artificial intelligence systems, such as question answering, relation extraction, and recommendation. Nevertheless, most real-world KGs are highly incomplete, with many missing relations between entities. To discover new triples (i.e., head entity, relation, tail entity), many KG completion algorithms have been proposed in recent years. However, a vast majority of existing studies often require a large number of training triples for each relation, which contradicts the fact that the frequency distribution of relations in KGs often follows a long tail distribution, meaning a majority of relations have only very few triples. Meanwhile, since most existing large-scale KGs are constructed automatically by extracting information from crowd-sourcing data using heuristic algorithms, plenty of errors could be inevitably incorporated due to the lack of human verification, which greatly reduces the performance for KG completion. To tackle the aforementioned issues, in this paper, we study a novel problem of error-aware few-shot KG completion and present a principled KG completion framework REFORM. Specifically, we formulate the problem under the few-shot learning framework, and our goal is to accumulate meta-knowledge across different meta-tasks and generalize the accumulated knowledge to the meta-test task for error-aware few-shot KG completion. To address the associated challenges resulting from insufficient training samples and inevitable errors, we propose three essential modules neighbor encoder, cross-relation aggregation, and error mitigation in each meta-task. Extensive experiments on three widely used KG datasets demonstrate the superiority of the proposed framework REFORM over competitive baseline methods. 

   more » « less
4. SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs

   https://doi.org/10.1145/3534678.3539405  

   Ren, Hongyu; Dai, Hanjun; Dai, Bo; Chen, Xinyun; Zhou, Denny; Leskovec, Jure; Schuurmans, Dale (August 2022, Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining)

   Knowledge graphs (KGs) capture knowledge in the form of head– relation–tail triples and are a crucial component in many AI systems. There are two important reasoning tasks on KGs: (1) single-hop knowledge graph completion, which involves predicting individual links in the KG; and (2), multi-hop reasoning, where the goal is to predict which KG entities satisfy a given logical query. Embedding-based methods solve both tasks by first computing an embedding for each entity and relation, then using them to form predictions. However, existing scalable KG embedding frameworks only support single-hop knowledge graph completion and cannot be applied to the more challenging multi-hop reasoning task. Here we present Scalable Multi-hOp REasoning (SMORE), the first general framework for both single-hop and multi-hop reasoning in KGs. Using a single machine SMORE can perform multi-hop reasoning in Freebase KG (86M entities, 338M edges), which is 1,500× larger than previously considered KGs. The key to SMORE’s runtime performance is a novel bidirectional rejection sampling that achieves a square root reduction of the complexity of online training data generation. Furthermore, SMORE exploits asynchronous scheduling, overlapping CPU-based data sampling, GPU-based embedding computation, and frequent CPU–GPU IO. SMORE increases throughput (i.e., training speed) over prior multi-hop KG frameworks by 2.2× with minimal GPU memory requirements (2GB for training 400-dim embeddings on 86M-node Freebase) and achieves near linear speed-up with the number of GPUs. Moreover, on the simpler single-hop knowledge graph completion task SMORE achieves comparable or even better runtime performance to state-of-the-art frameworks on both single GPU and multi-GPU settings. 

   more » « less
5. BUILD-KG: Integrating Heterogeneous Data Into Analytics-Enabling Knowledge Graphs

   https://doi.org/10.1109/BigData59044.2023.10386570  

   Schatz, Kara; Hou, Pei-Yu; Gulyuk, Alexey V; Yingling, Yaroslava G; Chirkova, Rada (December 2023, IEEE)

   Knowledge graphs (KGs), with their flexible encoding of heterogeneous data, have been increasingly used in a variety of applications. At the same time, domain data are routinely stored in formats such as spreadsheets, text, or figures. Storing such data in KGs can open the door to more complex types of analytics, which might not be supported by the data sources taken in isolation. Giving domain experts the option to use a predefined automated workflow for integrating heterogeneous data from multiple sources into a single unified KG could significantly alleviate their data-integration time and resource burden, while potentially resulting in higher-quality KG data capable of enabling meaningful rule mining and machine learning.In this paper we introduce a domain-agnostic workflow called BUILD-KG for integrating heterogeneous scientific and experimental data from multiple sources into a single unified KG potentially enabling richer analytics. BUILD-KG is broadly applicable, accepting input data in popular structured and unstructured formats. BUILD-KG is also designed to be carried out with end users as humans-in-the-loop, which makes it domain aware. We present the workflow, report on our experiences with applying it to scientific and experimental data in the materials science domain, and provide suggestions for involving domain scientists in BUILD-KG as humans-in-the-loop. 

   more » « less