Relational Message Passing for Knowledge Graph Completion

Wang, Hongwei; Ren, H.; Leskovec, Jure

doi:10.48550/arxiv.2002.06757

Cited by 14 publications

(22 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rule mining methods, such as NeuralLP [63] and DRUM [41], learn probabilistic logical rules to weight different paths. Path representation methods, such as Path-RNN [35] and its successors [9,56], encode each path with recurrent neural networks (RNNs), and aggregate paths for prediction. However, these methods need to traverse an exponential number of paths and are limited to very short paths, e.g., ≤ 3 edges.…”

Section: Related Workmentioning

confidence: 99%

“…While the above formulation captures important heuristics for link prediction, it is computationally expensive since the number of paths grows exponentially with the path length. Previous works [35,9,56] that directly computes the exponential number of paths can only afford a maximal path length of 3. A more scalable solution is to use the generalized Bellman-Ford algorithm [3].…”

Section: Path Formulation For Link Predictionmentioning

confidence: 99%

See 1 more Smart Citation

Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction

Zhu

Zhang²,

Xhonneux

et al. 2021

Preprint

View full text Add to dashboard Cite

Link prediction is a very fundamental task on graphs. Inspired by traditional path-based methods, in this paper we propose a general and flexible representation learning framework based on paths for link prediction. Specifically, we define the representation of a pair of nodes as the generalized sum of all path representations, with each path representation as the generalized product of the edge representations in the path. Motivated by the Bellman-Ford algorithm for solving the shortest path problem, we show that the proposed path formulation can be efficiently solved by the generalized Bellman-Ford algorithm. To further improve the capacity of the path formulation, we propose the Neural Bellman-Ford Network (NBFNet), a general graph neural network framework that solves the path formulation with learned operators in the generalized Bellman-Ford algorithm. The NBFNet parameterizes the generalized Bellman-Ford algorithm with 3 neural components, namely INDICATOR, MESSAGE and AGGREGATE functions, which corresponds to the boundary condition, multiplication operator, and summation operator respectively 1 . The NBFNet is very general, covers many traditional path-based methods, and can be applied to both homogeneous graphs and multi-relational graphs (e.g., knowledge graphs) in both transductive and inductive settings. Experiments on both homogeneous graphs and knowledge graphs show that the proposed NBFNet outperforms existing methods by a large margin in both transductive and inductive settings, achieving new state-of-the-art results.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Path Formulation For Link Predictionmentioning

confidence: 99%

Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction

Zhu

Zhang²,

Xhonneux

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Some related work formulates this problem as link prediction, i.e., predicting the missing tail/head entity given a head/tail entity and a relation. The two problems have proven to be actually reducible to each other [13].…”

Section: Notation and Problem Formulationmentioning

confidence: 99%

“…We evaluate LightCAKE on four popular benchmark datasets WN18RR [3], FB15K-237 [10], NELL995 [16] and DDB14 [13]. WN18RR is extracted from WordNet, containing conceptual-semantic and lexical relations among English words.…”

Section: Datasetmentioning

confidence: 99%

LightCAKE: A Lightweight Framework for Context-Aware Knowledge Graph Embedding

Ning

Qiao

Dong

et al. 2021

Preprint

View full text Add to dashboard Cite

Knowledge graph embedding (KGE) models learn to project symbolic entities and relations into a continuous vector space based on the observed triplets. However, existing KGE models cannot make a proper trade-off between the graph context and the model complexity, which makes them still far from satisfactory. In this paper, we propose a lightweight framework named LightCAKE for context-aware KGE. LightCAKE explicitly models the graph context without introducing redundant trainable parameters, and uses an iterative aggregation strategy to integrate the context information into the entity/relation embeddings. As a generic framework, it can be used with many simple KGE models to achieve excellent results. Finally, extensive experiments on public benchmarks demonstrate the efficiency and effectiveness of our framework.

show abstract

“…(3) Knowledge Graph Completion [40]. A variety of applications such as recommendation systems, search and question answering depend on knowledge graphs (KGs).…”

Section: Introductionmentioning

confidence: 99%

PathEnum: Towards Real-Time Hop-Constrained s-t Path Enumeration

Sun

Chen

et al. 2021

Preprint

View full text Add to dashboard Cite

We study the hop-constrained s-t path enumeration (HcPE) problem, which takes a graph 𝐺, two distinct vertices 𝑠, 𝑡 and a hop constraint 𝑘 as input, and outputs all paths from 𝑠 to 𝑡 whose length is at most 𝑘. The state-of-the-art algorithms suffer from severe performance issues caused by the costly pruning operations during enumeration for the workloads with the large search space. Consequently, these algorithms hardly meet the real-time constraints of many online applications. In this paper, we propose PathEnum, an efficient index-based algorithm towards real-time HcPE. For an input query, PathEnum first builds a light-weight index aiming to reduce the number of edges involved in the enumeration, and develops efficient index-based approaches for enumeration, one based on depth-first search and the other based on joins. We further develop a query optimizer based on a join-based cost model to optimize the search order. We conduct experiments with 15 real-world graphs. Our experiment results show that PathEnum outperforms the state-of-the-art approaches by orders of magnitude in terms of the query time, throughput and response time.

show abstract

Relational Message Passing for Knowledge Graph Completion

Cited by 14 publications

References 33 publications

Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction

Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction

LightCAKE: A Lightweight Framework for Context-Aware Knowledge Graph Embedding

PathEnum: Towards Real-Time Hop-Constrained s-t Path Enumeration

Contact Info

Product

Resources

About