ProjE: Embedding Projection for Knowledge Graph Completion

By Baoxu Shi, Tim Weninger. 2016

277 citations recorded by the source corpus.

With the large volume of new information created every day, determining the validity of information in a knowledge graph and filling in its missing parts are crucial tasks for many researchers and practitioners. To address this challenge, a number of knowledge graph completion methods have been developed using low-dimensional graph embeddings. Although researchers continue to improve these models using an increasingly complex feature space, we show that simple changes in the architecture of the underlying model can outperform state-of-the-art models without the need for complex feature engineering. In this work, we present a shared variable neural network model called ProjE that fills-in missing information in a knowledge graph by learning joint embeddings of the knowledge graph’s entities and edges, and through subtle, but important, changes to the standard loss function. In doing so, ProjE has a parameter size that is smaller than 11 out of 15 existing methods while performing 37% better than the current-best method on standard datasets. We also show, via a new fact checking task, that ProjE is capable of accurately determining the veracity of many declarative statements.

Subfields: Artificial Intelligence, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

Citations in the corpus

A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, methodology): “ChebNet graph GCN [72] Graph Convolutional Network graph GNN [120] Graph Neural Network graph [121] adapted Graph Neural Network molecules graph GGS-NNs [122] adapted Graph Neural Network graph HNE [33] CNN + FC graph with image and text DUIF [35] a hierarchical deep model social curation network Pr”
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, background): “Aforementioned KRL methods (e.g., TransE [16], TransH [20], TransR [17], HolE [21], and R-GCN [60]) and joint learning methods like DKRL [65] with textual information can been used for KGC. Unlike representing inputs and candidates in the uniﬁed embedding space, ProjE [82] proposes a combined embedd”
A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network (2017, methodology): “, 2013) and ProjE (Shi and Weninger, 2017) use a bilinear tensor operator while HolE (Nickel et al.”
Open-World Knowledge Graph Completion (2017, methodology): “In other recent work, ProjE (Shi and Weninger 2017) considered closed-world KGC to be a type of ranking task and applied a list-wise ranking loss instead of Eq.”
Recent advances in deep learning based dialogue systems: a systematic survey (2021, background): “, 2016) and ProjE (Shi and Weninger, 2017) belong to this category.”
RuleHub (2020, background): “Finally, the generation of new facts in a graph is related to the task of link prediction [9, 23, 33].”
A benchmarking study of embedding-based entity alignment for knowledge graphs (2020, unknown): “Existing KG embedding models can be generally divided into three categories: (i) translational models , e.g., TransE [5], TransH [82], TransR [49] and TransD [33]; (ii) semantic matching models , e.g., DistMult [86], ComplEx [76], HolE [54], SimplE [36], RotatE [71] and TuckER [3]; and (iii) deep mo”
Knowledge Graph Completion: A Review (2020, methodology): “Through experiments on knowledge graph benchmark data sets FB15K [101], WN18 [102] and FB15K [103], DSKG is better than a variety of previous models in many evaluation indicators.”
Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs (2019, methodology): “Many KG embedding models belong to this kind, including not only translational models like TransE (Bordes et al., 2013), TransH (Wang et al., 2014) and TransR (Lin et al., 2015b), but also compositional models like DistMult (Yang et al., 2015), ComplEx (Trouillon et al., 2016) and HolE (Nickel et al”
A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, methodology): “Then, NAM [62] proposes the relational-modulated neural network (RMNN), and NN models share variables in ProjE [63], which jointly learns embeddings of the entities and relations via the standard loss function.”
KG-BERT: BERT for Knowledge Graph Completion (2019, background): “ProjE achieves very competitive results by treating KG completion as a ranking problem and optimizing ranking score vectors.”