Graph-Revised Convolutional Network

Yu, Dawei; Zhang, Ruohong; Jiang, Zhengbao; Wu, Yuexin; Yang, Yiming

doi:10.1007/978-3-030-67664-3_23

Cited by 64 publications

(64 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the discrete nature of graph structures, one type of methods adopts probabilistic models, such as Bernoulli probability model [12] and stochastic block model [45]. Another type of methods models structures with node-wise similarity computed by metric learning functions like cosine similarity [7] and dot production [11,53]. Besides, directly treating each element in adjacency matrix as a learnable parameter is also an effective solution [11,20].…”

Section: Deep Graph Structure Learningmentioning

confidence: 99%

“…To tackle the aforementioned problems, deep graph structure learning (GSL) is a promising solution that constructs and improves the graph topology with GNNs [7,12,20,58]. Concretely, these methods parameterize the adjacency matrix with a probabilistic model [12,45], full parameterization [20] or metric learning model [7,11,53], and jointly optimize the parameters of the adjacency matrix and GNNs by solving a downstream task (i.e., node classification) [58]. However, existing methods learn graph structures in a supervised scenario, which brings the following issues: (1) The reliance on label information.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards Unsupervised Deep Graph Structure Learning

Liu¹,

Zheng²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

In recent years, graph neural networks (GNNs) have emerged as a successful tool in a variety of graph-related applications. However, the performance of GNNs can be deteriorated when noisy connections occur in the original graph structures; besides, the dependence on explicit structures prevents GNNs from being applied to general unstructured scenarios. To address these issues, recently emerged deep graph structure learning (GSL) methods propose to jointly optimize the graph structure along with GNN under the supervision of a node classification task. Nonetheless, these methods focus on a supervised learning scenario, which leads to several problems, i.e., the reliance on labels, the bias of edge distribution, and the limitation on application tasks. In this paper, we propose a more practical GSL paradigm, unsupervised graph structure learning, where the learned graph topology is optimized by data itself without any external guidance (i.e., labels). To solve the unsupervised GSL problem, we propose a novel StrUcture Bootstrapping contrastive LearnIng fraMEwork (SUBLIME for abbreviation) with the aid of self-supervised contrastive learning. Specifically, we generate a learning target from the original data as an "anchor graph", and use a contrastive loss to maximize the agreement between the anchor graph and the learned graph. To provide persistent guidance, we design a novel bootstrapping mechanism that upgrades the anchor graph with learned structures during model learning. We also design a series of graph learners and post-processing schemes to model the structures to learn. Extensive experiments on eight benchmark datasets demonstrate the significant effectiveness of our proposed SUBLIME and high quality of the optimized graphs. CCS CONCEPTS• Mathematics of computing → Graph algorithms; • Computing methodologies → Neural networks.

show abstract

Section: Deep Graph Structure Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Towards Unsupervised Deep Graph Structure Learning

Liu¹,

Zheng²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Others learn to reweight edges in a fully connected graph (i.e., soft pruning). and Yu et al (2019) propose heuristics for regularizing edge weights. Hu et al (2019) use the question embedding to help predict edge weights.…”

Section: Related Workmentioning

confidence: 99%

Learning Contextualized Knowledge Structures for Commonsense Reasoning

Yan¹,

Raman²,

Chan³

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

Recently, knowledge graph (KG) augmented models have achieved noteworthy success on various commonsense reasoning tasks. However, KG edge (fact) sparsity and noisy edge extraction/generation often hinder models from obtaining useful knowledge to reason over. To address these issues, we propose a new KG-augmented model: Hybrid Graph Network (HGN). Unlike prior methods, HGN learns to jointly contextualize extracted and generated knowledge by reasoning over both within a unified graph structure. Given the task input context and an extracted KG subgraph, HGN is trained to generate embeddings for the subgraph's missing edges to form a "hybrid" graph, then reason over the hybrid graph while filtering out context-irrelevant edges. We demonstrate HGN's effectiveness through considerable performance gains across four commonsense reasoning benchmarks, plus a user study on edge validness and helpfulness. 1

show abstract

“…However, early work in GCNs also have a limitation in common, i.e., graph convolution is only used to learn node embedding conditioned on fixed edges [12], instead of jointly learning the optimal embeddings for both nodes and edges. Later efforts move on the direction of learning of wights of edges in the input graph in parallel with the learning of node embedding [31,44], which is more powerful than early GCNs and more capable in model adaptation for downstream tasks. However, those GCNs have a constraint in common, that is, the edges in the input graph must be of homogeneous kind, such as the links in a citation graph or the elements in a co-occurrence count matrix.…”

Section: Introductionmentioning

confidence: 99%

Knowledge Embedding Based Graph Convolutional Network

Yang

Zhang

et al. 2021

Proceedings of the Web Conference 2021

Self Cite

View full text Add to dashboard Cite

Recently, a considerable literature has grown up around the theme of Graph Convolutional Network (GCN). How to effectively leverage the rich structural information in complex graphs, such as knowledge graphs with heterogeneous types of entities and relations, is a primary open challenge in the field. Most GCN methods are either restricted to graphs with a homogeneous type of edges (e.g., citation links only), or focusing on representation learning for nodes only instead of jointly propagating and updating the embeddings of both nodes and edges for target-driven objectives. This paper addresses these limitations by proposing a novel framework, namely the Knowledge Embedding based Graph Convolutional Network (KE-GCN), which combines the power of GCNs in graphbased belief propagation and the strengths of advanced knowledge embedding (a.k.a. knowledge graph embedding) methods, and goes beyond. Our theoretical analysis shows that KE-GCN offers an elegant unification of several well-known GCN methods as specific cases, with a new perspective of graph convolution. Experimental results on benchmark datasets show the advantageous performance of KE-GCN over strong baseline methods in the tasks of knowledge graph alignment and entity classification 1 . CCS CONCEPTS• Computing methodologies → Neural networks; Reasoning about belief and knowledge.

show abstract

Graph-Revised Convolutional Network

Cited by 64 publications

References 14 publications

Towards Unsupervised Deep Graph Structure Learning

Towards Unsupervised Deep Graph Structure Learning

Learning Contextualized Knowledge Structures for Commonsense Reasoning

Knowledge Embedding Based Graph Convolutional Network

Contact Info

Product

Resources

About