MetaFill: Text Infilling for Meta-Path Generation on Heterogeneous Information Networks

• URL: http://arxiv.org/abs/2210.07488v1
• Date: Fri, 14 Oct 2022 03:34:09 GMT
• Title: MetaFill: Text Infilling for Meta-Path Generation on Heterogeneous Information Networks
• Authors: Zequn Liu, Kefei Duan, Junwei Yang, Hanwen Xu, Ming Zhang, Sheng Wang
• Abstract summary: Heterogeneous Information Network (HIN) is essential to study complicated networks containing multiple edge types and node types. Existing meta-path generation approaches cannot fully exploit the rich textual information in HINs. We propose MetaFill, a text-infilling-based approach for meta-path generation.
• Score: 7.501059084460409
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Heterogeneous Information Network (HIN) is essential to study complicated networks containing multiple edge types and node types. Meta-path, a sequence of node types and edge types, is the core technique to embed HINs. Since manually curating meta-paths is time-consuming, there is a pressing need to develop automated meta-path generation approaches. Existing meta-path generation approaches cannot fully exploit the rich textual information in HINs, such as node names and edge type names. To address this problem, we propose MetaFill, a text-infilling-based approach for meta-path generation. The key idea of MetaFill is to formulate meta-path identification problem as a word sequence infilling problem, which can be advanced by Pretrained Language Models (PLMs). We observed the superior performance of MetaFill against existing meta-path generation methods and graph embedding methods that do not leverage meta-paths in both link prediction and node classification on two real-world HIN datasets. We further demonstrated how MetaFill can accurately classify edges in the zero-shot setting, where existing approaches cannot generate any meta-paths. MetaFill exploits PLMs to generate meta-paths for graph embedding, opening up new avenues for language model applications in graph analysis.

Related papers

• Context-Aware Meta-Learning [52.09326317432577]
  We propose a meta-learning algorithm that emulates Large Language Models by learning new visual concepts during inference without fine-tuning. Our approach exceeds or matches the state-of-the-art algorithm, P>M>F, on 8 out of 11 meta-learning benchmarks.
  arXiv  Detail & Related papers  (2023-10-17T03:35:27Z)
• Inductive Meta-path Learning for Schema-complex Heterogeneous Information Networks [46.325577161493726]
  Heterogeneous Information Networks (HINs) are information networks with multiple types of nodes and edges. The concept of meta-path, i.e., a sequence of entity types and relation types connecting two entities, is proposed to provide the meta-level explainable semantics for various HIN tasks.
  arXiv  Detail & Related papers  (2023-07-08T09:10:43Z)
• MECCH: Metapath Context Convolution-based Heterogeneous Graph Neural Networks [45.68142605304948]
  Heterogeneous graph neural networks (HGNNs) were proposed for representation learning on structural data with multiple types of nodes and edges. We present a novel Metapath Context Convolution-based Heterogeneous Graph Neural Network (MECCH)
  arXiv  Detail & Related papers  (2022-11-23T09:13:33Z)
• Meta-node: A Concise Approach to Effectively Learn Complex Relationships in Heterogeneous Graphs [18.65171129524357]
  We propose a novel concept of meta-node for message passing that can learn enriched relational knowledge from complex heterogeneous graphs without any meta-paths and meta-graphs. Unlike meta-paths and meta-graphs, meta-nodes do not require any pre-processing steps that require expert knowledge. In the experiments on node clustering and classification tasks, the proposed meta-node message passing method outperforms state-of-the-arts that depend on meta-paths.
  arXiv  Detail & Related papers  (2022-10-26T05:04:29Z)
• MetaFormer: A Unified Meta Framework for Fine-Grained Recognition [16.058297377539418]
  We propose a unified and strong meta-framework for fine-grained visual classification. In practice, MetaFormer provides a simple yet effective approach to address the joint learning of vision and various meta-information. In experiments, MetaFormer can effectively use various meta-information to improve the performance of fine-grained recognition.
  arXiv  Detail & Related papers  (2022-03-05T14:12:25Z)
• SHGNN: Structure-Aware Heterogeneous Graph Neural Network [77.78459918119536]
  This paper proposes a novel Structure-Aware Heterogeneous Graph Neural Network (SHGNN) to address the above limitations. We first utilize a feature propagation module to capture the local structure information of intermediate nodes in the meta-path. Next, we use a tree-attention aggregator to incorporate the graph structure information into the aggregation module on the meta-path. Finally, we leverage a meta-path aggregator to fuse the information aggregated from different meta-paths.
  arXiv  Detail & Related papers  (2021-12-12T14:18:18Z)
• MetaDelta: A Meta-Learning System for Few-shot Image Classification [71.06324527247423]
  We propose MetaDelta, a novel practical meta-learning system for the few-shot image classification. Each meta-learner in MetaDelta is composed of a unique pretrained encoder fine-tuned by batch training and parameter-free decoder used for prediction.
  arXiv  Detail & Related papers  (2021-02-22T02:57:22Z)
• Metapath- and Entity-aware Graph Neural Network for Recommendation [10.583077434945187]
  In graph neural networks (GNNs) message passing iteratively aggregates nodes' information from their direct neighbors. Such sequential node connections e.g., metapaths, capture critical insights for downstream tasks. We employ collaborative subgraphs (CSGs) and metapaths to form metapath-aware subgraphs. PEAGNN trains multilayer GNNs to perform metapath-aware information aggregation on such subgraphs.
  arXiv  Detail & Related papers  (2020-10-22T15:14:30Z)
• Meta-Learning across Meta-Tasks for Few-Shot Learning [107.44950540552765]
  We argue that the inter-meta-task relationships should be exploited and those tasks are sampled strategically to assist in meta-learning. We consider the relationships defined over two types of meta-task pairs and propose different strategies to exploit them.
  arXiv  Detail & Related papers  (2020-02-11T09:25:13Z)
• Incremental Meta-Learning via Indirect Discriminant Alignment [118.61152684795178]
  We develop a notion of incremental learning during the meta-training phase of meta-learning. Our approach performs favorably at test time as compared to training a model with the full meta-training set.
  arXiv  Detail & Related papers  (2020-02-11T01:39:12Z)

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.