FedMKGC: Privacy-Preserving Federated Multilingual Knowledge Graph Completion

• URL: http://arxiv.org/abs/2312.10645v1
• Date: Sun, 17 Dec 2023 08:09:27 GMT
• Title: FedMKGC: Privacy-Preserving Federated Multilingual Knowledge Graph Completion
• Authors: Wei Tang, Zhiqian Wu, Yixin Cao, Yong Liao, Pengyuan Zhou
• Abstract summary: Knowledge graph completion (KGC) aims to predict missing facts in knowledge graphs (KGs) Previous methods that rely on transferring raw data among KGs raise privacy concerns. We propose a new federated learning framework that implicitly aggregates knowledge from multiple KGs without demanding raw data exchange and entity alignment.
• Score: 21.4302940596294
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge graph completion (KGC) aims to predict missing facts in knowledge graphs (KGs), which is crucial as modern KGs remain largely incomplete. While training KGC models on multiple aligned KGs can improve performance, previous methods that rely on transferring raw data among KGs raise privacy concerns. To address this challenge, we propose a new federated learning framework that implicitly aggregates knowledge from multiple KGs without demanding raw data exchange and entity alignment. We treat each KG as a client that trains a local language model through textbased knowledge representation learning. A central server then aggregates the model weights from clients. As natural language provides a universal representation, the same knowledge thus has similar semantic representations across KGs. As such, the aggregated language model can leverage complementary knowledge from multilingual KGs without demanding raw user data sharing. Extensive experiments on a benchmark dataset demonstrate that our method substantially improves KGC on multilingual KGs, achieving comparable performance to state-of-the-art alignment-based models without requiring any labeled alignments or raw user data sharing. Our codes will be publicly available.

Related papers

• Learning Rules from KGs Guided by Language Models [48.858741745144044]
  Rule learning methods can be applied to predict potentially missing facts. Ranking of rules is especially challenging over highly incomplete or biased KGs. With the recent rise of Language Models (LMs) several works have claimed that LMs can be used as alternative means for KG completion.
  arXiv  Detail & Related papers  (2024-09-12T09:27:36Z)
• KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge [63.19837262782962]
  Knowledge Graph Embedding (KGE) techniques are crucial in learning compact representations of entities and relations within a knowledge graph. This study introduces KG-FIT, which builds a semantically coherent hierarchical structure of entity clusters. Experiments on the benchmark datasets FB15K-237, YAGO3-10, and PrimeKG demonstrate the superiority of KG-FIT over state-of-the-art pre-trained language model-based methods.
  arXiv  Detail & Related papers  (2024-05-26T03:04:26Z)
• Collective Knowledge Graph Completion with Mutual Knowledge Distillation [11.922522192224145]
  We study the problem of multi-KG completion, where we focus on maximizing the collective knowledge from different KGs. We propose a novel method called CKGC-CKD that uses relation-aware graph convolutional network encoder models on both individual KGs and a large fused KG. Experimental results on multilingual datasets have shown that our method outperforms all state-of-the-art models in the KGC task.
  arXiv  Detail & Related papers  (2023-05-25T09:49:40Z)
• Endowing Language Models with Multimodal Knowledge Graph Representations [47.22480859519051]
  We use the recently released VisualSem KG as our external knowledge repository. We retrieve entities from the KG and use their multimodal representations to improve downstream task performance.
  arXiv  Detail & Related papers  (2022-06-27T10:10:42Z)
• CoSe-Co: Text Conditioned Generative CommonSense Contextualizer [13.451001884972033]
  Pre-trained Language Models (PTLMs) have been shown to perform well on natural language tasks. We propose a CommonSense Contextualizer (CoSe-Co) conditioned on sentences as input to make it generically usable in tasks.
  arXiv  Detail & Related papers  (2022-06-12T09:57:32Z)
• Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models [42.38563175680914]
  This paper studies how to automatically generate a natural language text that describes the facts in knowledge graph (KG) Considering the few-shot setting, we leverage the excellent capacities of pretrained language models (PLMs) in language understanding and generation.
  arXiv  Detail & Related papers  (2021-06-03T06:48:00Z)
• Multilingual Knowledge Graph Completion with Joint Relation and Entity Alignment [32.47122460214232]
  We present ALIGNKGC, which uses some seed alignments to jointly optimize all three of KGC, relation alignment and RA losses. ALIGNKGC achieves 10-32 MRR improvements over a strong state-of-the-art single-KGC system completion model over each monolingual KG.
  arXiv  Detail & Related papers  (2021-04-18T10:27:44Z)
• Language Models are Open Knowledge Graphs [75.48081086368606]
  Recent deep language models automatically acquire knowledge from large-scale corpora via pre-training. In this paper, we propose an unsupervised method to cast the knowledge contained within language models into KGs. We show that KGs are constructed with a single forward pass of the pre-trained language models (without fine-tuning) over the corpora.
  arXiv  Detail & Related papers  (2020-10-22T18:01:56Z)
• Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer [43.453915033312114]
  Predicting missing facts in a knowledge graph (KG) is a crucial task in knowledge base construction and reasoning. We propose KEnS, a novel framework for embedding learning and ensemble knowledge transfer across a number of language-specific KGs. Experiments on five real-world language-specific KGs show that KEnS consistently improves state-of-the-art methods on KG completion.
  arXiv  Detail & Related papers  (2020-10-07T04:54:03Z)
• Cross-lingual Entity Alignment with Incidental Supervision [76.66793175159192]
  We propose an incidentally supervised model, JEANS, which jointly represents multilingual KGs and text corpora in a shared embedding scheme. Experiments on benchmark datasets show that JEANS leads to promising improvement on entity alignment with incidental supervision.
  arXiv  Detail & Related papers  (2020-05-01T01:53:56Z)
• On the Role of Conceptualization in Commonsense Knowledge Graph Construction [59.39512925793171]
  Commonsense knowledge graphs (CKGs) like Atomic and ASER are substantially different from conventional KGs. We introduce to CKG construction methods conceptualization to view entities mentioned in text as instances of specific concepts or vice versa. Our methods can effectively identify plausible triples and expand the KG by triples of both new nodes and edges of high diversity and novelty.
  arXiv  Detail & Related papers  (2020-03-06T14:35:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.