{"url":"/method/dgcnn","slug":"dgcnn","name":"DGCNN","full_name":"Deep Graph Convolutional Neural Network","full_name_withheld":false,"description_markdown":"DGCNN involves neural networks that read the graphs directly and learn a classification function. There are two main challenges: 1) how to extract useful features characterizing the rich information encoded in a graph for classification purpose, and 2) how to sequentially read a graph in a meaningful and consistent order. To address the first challenge, we design a localized graph convolution model and show its connection with two graph kernels. To address the second challenge, we design a novel SortPooling layer which sorts graph vertices in a consistent order so that traditional neural networks can be trained on the graphs.\r\n\r\nDescription and image from: [An End-to-End Deep Learning Architecture for Graph Classification](https://muhanzhang.github.io/papers/AAAI_2018_DGCNN.pdf)","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/viewPaper/17146","title":"An End-to-End Deep Learning Architecture for Graph Classification","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Graphs","area_id":"graphs","collection":"Graph Models","url":"/methods/category/graph-models","pwc_aliases":[]}],"n_papers_tagged":49,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/knn-defense-defense-against-3d-adversarial","title":"KNN-Defense: Defense against 3D Adversarial Point Clouds using Nearest-Neighbor Search","date":"2025-06-07","arxiv_id":"2506.06906","n_code_links":1,"syntology":null},{"paper":null,"title":"Interpretable Affordance Detection on 3D Point Clouds with Probabilistic Prototypes","date":"2025-04-25","arxiv_id":"2504.18355","n_code_links":0,"syntology":null},{"paper":"/paper/introducing-the-short-time-fourier-kolmogorov","title":"Introducing the Short-Time Fourier Kolmogorov Arnold Network: A Dynamic Graph CNN Approach for Tree Species Classification in 3D Point Clouds","date":"2025-03-31","arxiv_id":"2503.23647","n_code_links":1,"syntology":null},{"paper":"/paper/adacrossnet-adaptive-dynamic-loss-weighting","title":"AdaCrossNet: Adaptive Dynamic Loss Weighting for Cross-Modal Contrastive Point Cloud Learning","date":"2025-01-02","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/impact-of-color-and-mixing-proportion-of","title":"Impact of color and mixing proportion of synthetic point clouds on semantic segmentation","date":"2024-12-26","arxiv_id":"2412.19145","n_code_links":1,"syntology":null},{"paper":null,"title":"Enhancing 3D Robotic Vision Robustness by Minimizing Adversarial Mutual Information through a Curriculum Training Approach","date":"2024-09-19","arxiv_id":"2409.12379","n_code_links":0,"syntology":null},{"paper":null,"title":"HGNAS: Hardware-Aware Graph Neural Architecture Search for Edge Devices","date":"2024-08-23","arxiv_id":"2408.12840","n_code_links":0,"syntology":null},{"paper":"/paper/meeg-and-at-dgnn-advancing-eeg-emotion","title":"MEEG and AT-DGNN: Improving EEG Emotion Recognition with Music Introducing and Graph-based Learning","date":"2024-07-08","arxiv_id":"2407.05550","n_code_links":1,"syntology":null},{"paper":"/paper/interpretable3d-an-ad-hoc-interpretable","title":"Interpretable3D: An Ad-Hoc Interpretable Classifier for 3D Point Clouds","date":"2024-03-24","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Locating and Mitigating Gender Bias in Large Language Models","date":"2024-03-21","arxiv_id":"2403.14409","n_code_links":0,"syntology":null},{"paper":"/paper/epsilon-mesh-attack-a-surface-based","title":"epsilon-Mesh Attack: A Surface-based Adversarial Point Cloud Attack for Facial Expression Recognition","date":"2024-03-11","arxiv_id":"2403.06661","n_code_links":2,"syntology":null},{"paper":null,"title":"A Deep Reinforcement Learning Approach for Adaptive Traffic Routing in Next-gen Networks","date":"2024-02-07","arxiv_id":"2402.04515","n_code_links":0,"syntology":null},{"paper":null,"title":"CausalPC: Improving the Robustness of Point Cloud Classification by Causal Effect Identification","date":"2024-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/shape-matters-detecting-vertebral-fractures","title":"Shape Matters: Detecting Vertebral Fractures Using Differentiable Point-Based Shape Decoding","date":"2023-12-08","arxiv_id":"2312.05220","n_code_links":1,"syntology":null},{"paper":null,"title":"Technical Report of 2023 ABO Fine-grained Semantic Segmentation Competition","date":"2023-09-30","arxiv_id":"2310.00427","n_code_links":0,"syntology":null},{"paper":"/paper/gnn4eeg-a-benchmark-and-toolkit-for","title":"GNN4EEG: A Benchmark and Toolkit for Electroencephalography Classification with Graph Neural Network","date":"2023-09-27","arxiv_id":"2309.15515","n_code_links":3,"syntology":null},{"paper":"/paper/milipoint-a-point-cloud-dataset-for-mmwave","title":"MiliPoint: A Point Cloud Dataset for mmWave Radar","date":"2023-09-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"A Tiny Machine Learning Model for Point Cloud Object Classification","date":"2023-03-20","arxiv_id":"2303.10898","n_code_links":0,"syntology":null},{"paper":null,"title":"Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platforms","date":"2023-03-20","arxiv_id":"2303.10875","n_code_links":0,"syntology":null},{"paper":"/paper/depgraph-towards-any-structural-pruning","title":"DepGraph: Towards Any Structural Pruning","date":"2023-01-30","arxiv_id":"2301.12900","n_code_links":1,"syntology":{"ran":1,"of":7,"unverified":6,"pointer_only":0}},{"paper":"/paper/tetrasphere-a-neural-descriptor-for-o-3","title":"TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis","date":"2022-11-26","arxiv_id":"2211.14456","n_code_links":1,"syntology":{"ran":3,"of":10,"unverified":7,"pointer_only":0}},{"paper":null,"title":"Point-Syn2Real: Semi-Supervised Synthetic-to-Real Cross-Domain Learning for Object Classification in 3D Point Clouds","date":"2022-10-31","arxiv_id":"2210.17009","n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-learning-with-multi-view","title":"Self-Supervised Learning with Multi-View Rendering for 3D Point Cloud Analysis","date":"2022-10-28","arxiv_id":"2210.15904","n_code_links":1,"syntology":{"ran":1,"of":4,"unverified":3,"pointer_only":0}},{"paper":null,"title":"Understanding Key Point Cloud Features for Development Three-dimensional Adversarial Attacks","date":"2022-10-19","arxiv_id":"2210.14164","n_code_links":0,"syntology":null},{"paper":"/paper/svnet-where-so-3-equivariance-meets","title":"SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation","date":"2022-09-13","arxiv_id":"2209.05924","n_code_links":1,"syntology":null},{"paper":null,"title":"Explaining Deep Neural Networks for Point Clouds using Gradient-based Visualisations","date":"2022-07-26","arxiv_id":"2207.12984","n_code_links":0,"syntology":null},{"paper":null,"title":"AI-based Clinical Assessment of Optic Nerve Head Robustness Superseding Biomechanical Testing","date":"2022-06-09","arxiv_id":"2206.04689","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-human-pose-estimation-via-3d-event","title":"Efficient Human Pose Estimation via 3D Event Point Cloud","date":"2022-06-09","arxiv_id":"2206.04511","n_code_links":1,"syntology":{"ran":4,"of":8,"unverified":4,"pointer_only":0}},{"paper":null,"title":"Topologically Persistent Features-based Object Recognition in Cluttered Indoor Environments","date":"2022-05-16","arxiv_id":"2205.07479","n_code_links":0,"syntology":null},{"paper":null,"title":"Geometric Deep Learning to Identify the Critical 3D Structural Features of the Optic Nerve Head for Glaucoma Diagnosis","date":"2022-04-14","arxiv_id":"2204.06931","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/point-cloud-classification","name":"Point Cloud Classification","papers":8},{"task":"/task/3d-point-cloud-classification","name":"3D Point Cloud Classification","papers":6},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":5},{"task":"/task/adversarial-attack","name":"Adversarial Attack","papers":4},{"task":"/task/graph-neural-network","name":"Graph Neural Network","papers":4},{"task":"/task/adversarial-robustness","name":"Adversarial Robustness","papers":3},{"task":"/task/classification-1","name":"Classification","papers":3},{"task":"/task/decision-making","name":"Decision Making","papers":3},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":3},{"task":"/task/object","name":"Object","papers":3},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":3},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":3},{"task":"/task/3d-shape-retrieval","name":"3D Shape Classification","papers":2},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":2},{"task":"/task/eeg-1","name":"EEG","papers":2},{"task":"/task/edge-computing","name":"Edge-computing","papers":2},{"task":null,"name":"GPU","papers":2},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":2},{"task":"/task/object-detection","name":"Object Detection","papers":2},{"task":"/task/object-recognition","name":"Object Recognition","papers":2}],"tasks_shown":20,"n_tasks":81,"usage_by_year":[{"year":"2018","papers":2},{"year":"2019","papers":2},{"year":"2020","papers":3},{"year":"2021","papers":9},{"year":"2022","papers":13},{"year":"2023","papers":7},{"year":"2024","papers":9},{"year":"2025","papers":4}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/dgcnn"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}