Symbolic Graph Reasoning Meets Convolutions

By Xiaodan Liang, Zhiting Hu, Hao Zhang, Liang Lin, Eric P. Xing. 2018

168 citations recorded by the source corpus.

Subfields: Natural Language Processing, Graph Learning

How researchers see this paper

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

In Natural Language Processing

1. Zhiting Hu
2. Eric P. Xing
3. Xiaodan Liang
4. Yuan Li
5. Jingdong Wang
6. Yuhui Yuan
7. Alan L. Yuille
8. Yunchao Wei

In Graph Learning

1. Yehui Tang
2. Dacheng Tao
3. Eric P. Xing
4. Christian Bauckhage
5. Yuri Boykov
6. Yunhe Wang
7. Yuan Li
8. Jianyuan Guo

Citations in the corpus

• Visual Transformers: Token-based Image Representation and Processing for Computer Vision (2020, methodology): “hts from both works could be used together in one model for compounded benefit. Graph convolutions in vision models: Our work is also related to previous efforts such as GloRe [6], LatentGNN [47], and [26] that densely relate concepts in latent space using graph convolutions. To augment convolutions,”
• Object-Contextual Representations for Semantic Segmentation (2019, methodology): “2 - - - - SGR [40] ResNet-101 + ASPP 8× R - - 44.”
• Hierarchical Multi-Scale Attention for Semantic Segmentation (2020, background): “OCRNet [9], DANET [10], CFNet [11], OCNet [12] and other related work [13, 14, 15, 16, 17, 18, 19, 20] use such relationships to build better context.”
• Image Segmentation Using Deep Learning: A Survey (2020, background): “Additional models and methods include BoxSup [119], Graph Convolutional Networks (GCN) [120], Wide ResNet [121], Exfuse [122] (enhancing low-level and high-level features fusion), Feedforward-Net [123], saliency-aware models for geodesic video segmentation [124], Dual Image Segmentation (DIS) [125],”
• Expectation-Maximization Attention Networks for Semantic Segmentation (2019, unknown): “ResNet-50 50.5 SGR [18] ResNet-101 50.8 CCL [8] ResNet-101 51.6 EncNet [35] ResNet-101 51.7 SGR+ [18] ResNet-101 52.5 DANet [11] ResNet-101 EMANet ResNet-101 53.1 ResNet-101 33.6 CCL [8] ResNet-101 35.7 DANet [11] ResNet-50 37.2 DSSPN [19] ResNet-101 37.3 EMANet ResNet-50 37.6 SGR [18] ResNet-101…”
• When Radiology Report Generation Meets Knowledge Graph (2020, methodology): “As many existing works (Yao et al. 2018; Liang et al. 2018; Chen et al. 2018; Norcliffe-Brown, Vafeias, and Parisot 2018; Hu et al. 2019), we used the graph convolution as a means of message passing and node interaction.”
• Informed Machine Learning – A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems (2019, background): “Since the choice of graph can have high influence [81], we suggest a pool of standardized graphs in order to improve”
• Consistent Structural Relation Learning for Zero-Shot Segmentation (2020, methodology): “Although the development of FCN-based models [4, 5, 6] has significantly advanced semantic segmentation, the success of these approaches highly relies on cost-intensive and time-consuming dense mask annotations to train the network.”
• A Survey on Vision Transformer (2020, background): “There are other related works using attention based graph reasoning module [76, 21, 75] to enhance both the local and global representations.”
• Multiattention Network for Semantic Segmentation of Fine-Resolution Remote Sensing Images (2020, background): “Meanwhile, another burgeoning research area for semantic segmentation is how to embed the dot-product attention into a Graph Convolutional Network (GCN) and optimize the complexity of the attention [79-83].”
• Knowledge-driven Encode, Retrieve, Paraphrase for Medical Image Report Generation (2019, background): “Knowledge graph also allows incorporating priors, which is proven useful for tasks where universal knowledge is desired or certain constraints have to be met (Battaglia et al. 2017; Liang, Hu, and Xing 2018; Hu et al. 2018; X. Wang 2018).”
• Adaptive Context Network for Scene Parsing (2019, unknown): “Res-101 RefineNet [22] 33.6 Ding et al.[7] 35.7 DSSPN[20] 38.9 SGR [19] 39.1 DANet[16] 39.7 ACNet 40.1”
• Explainable Artificial Intelligence: a Systematic Review (2020, background): “[228] instead added to CNNs a new Symbolic Graph Reasoning (SGR) layer which performs reasoning over a group of symbolic nodes whose outputs explicitly represent different properties of each semantic in a prior knowledge graph.”