GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation

2 code implementations • ICML 2020

Results of experiments comparing different GNN architectures on three tasks from the literature are presented, based on re-implementations of baseline methods.

Vision GNN: An Image is Worth Graph of Nodes

7 code implementations • 1 Jun 2022

In this paper, we propose to represent the image as a graph structure and introduce a new Vision GNN (ViG) architecture to extract graph-level feature for visual tasks.

 Ranked #326 on Image Classification on ImageNet

 Image Classification  Object Detection

TF-GNN: Graph Neural Networks in TensorFlow

1 code implementation • 7 Jul 2022

TensorFlow GNN (TF-GNN) is a scalable library for Graph Neural Networks in TensorFlow.

 Graph Sampling

GraphFM: Improving Large-Scale GNN Training via Feature Momentum

1 code implementation • 14 Jun 2022

GraphFM-IB applies FM to in-batch sampled data, while GraphFM-OB applies FM to out-of-batch data that are 1-hop neighborhood of in-batch data.

 Node Classification

FederatedScope-GNN: Towards a Unified, Comprehensive and Efficient Package for Federated Graph Learning

1 code implementation • 12 Apr 2022

The incredible development of federated learning (FL) has benefited various tasks in the domains of computer vision and natural language processing, and the existing frameworks such as TFF and FATE has made the deployment easy in real-world applications.

 Federated Learning  Graph Learning

Graph Neural Networks: A Review of Methods and Applications

5 code implementations • 20 Dec 2018

Lots of learning tasks require dealing with graph data which contains rich relation information among elements.

 Graph Attention

Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction

4 code implementations • 12 Oct 2019

The key of this task is to model feature interactions among different feature fields.

  Ranked #1 on Click-Through Rate Prediction on Avazu

 Click-Through Rate Prediction  Recommendation Systems

MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions

2 code implementations • 23 May 2019

To resolve these problems, we present MR-GNN, an end-to-end graph neural network with the following features: i) it uses a multi-resolution based architecture to extract node features from different neighborhoods of each node, and, ii) it uses dual graph-state long short-term memory networks (L-STMs) to summarize local features of each graph and extracts the interaction features between pairwise graphs.

GPT-GNN: Generative Pre-Training of Graph Neural Networks

3 code implementations • 27 Jun 2020

Graph neural networks (GNNs) have been demonstrated to be powerful in modeling graph-structured data.

 Graph Generation

Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud

1 code implementation • CVPR 2020

In this paper, we propose a graph neural network to detect objects from a LiDAR point cloud.

 3D Object Detection  object-detection +1

QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering

4 code implementations • NAACL 2021

The problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) presents two challenges: given a QA context (question and answer choice), methods need to (i) identify relevant knowledge from large KGs, and (ii) perform joint reasoning over the QA context and KG.

 Ranked #2 on Riddle Sense on Riddle Sense

 Graph Representation Learning  Knowledge Graphs +4

Position-aware Graph Neural Networks

2 code implementations • 11 Jun 2019

Learning node embeddings that capture a node's position within the broader graph structure is crucial for many prediction tasks on graphs.

 Community Detection  Link Prediction

Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learning

1 code implementation • CVPR 2019

The meta-model, given as input some novel classes with few training examples per class, must properly adapt the existing recognition model into a new model that can correctly classify in a unified way both the novel and the base classes.

 Classification  Denoising +2

DAG-GNN: DAG Structure Learning with Graph Neural Networks

3 code implementations • 22 Apr 2019

Learning a faithful directed acyclic graph (DAG) from samples of a joint distribution is a challenging combinatorial problem, owing to the intractable search space superexponential in the number of graph nodes.

BertGCN: Transductive Text Classification by Combining GNN and BERT

1 code implementation • Findings (ACL) 2021

 text-classification  Text Classification

GRecX: An Efficient and Unified Benchmark for GNN-based Recommendation

1 code implementation • 19 Nov 2021

In this paper, we present GRecX, an open-source TensorFlow framework for benchmarking GNN-based recommendation models in an efficient and unified way.

 Benchmarking  Management

PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network For PM2.5 Forecasting

2 code implementations • ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems 2020

When predicting PM2. 5 concentrations, it is necessary to consider complex information sources since the concentrations are influenced by various factors within a long period.

TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs

1 code implementation • 28 Mar 2022

Our temporal parallel sampler achieves an average of 173x speedup on a multi-core CPU compared with the baselines.

 Link Prediction  Node Classification +1

Relational Multi-Task Learning: Modeling Relations between Data and Tasks

1 code implementation • ICLR 2022

Here we introduce a novel relational multi-task learning setting where we leverage data point labels from auxiliary tasks to make more accurate predictions on the new task.

 Multi-Task Learning

Design Space for Graph Neural Networks

2 code implementations • NeurIPS 2020

However, current research focuses on proposing and evaluating specific architectural designs of GNNs, as opposed to studying the more general design space of GNNs that consists of a Cartesian product of different design dimensions, such as the number of layers or the type of the aggregation function.

 Management

Identity-aware Graph Neural Networks

1 code implementation • 25 Jan 2021

However, the expressive power of existing GNNs is upper-bounded by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test, which means GNNs that are not able to predict node clustering coefficients and shortest path distances, and cannot differentiate between different d-regular graphs.

 Graph Classification  Graph Property Prediction +2

ROLAND: Graph Learning Framework for Dynamic Graphs

2 code implementations • 15 Aug 2022

Finally, we propose a scalable and efficient training approach for dynamic GNNs via incremental training and meta-learning.

 Graph Learning  Graph Representation Learning +2

edGNN: a Simple and Powerful GNN for Directed Labeled Graphs

1 code implementation • 18 Apr 2019

The ability of a graph neural network (GNN) to leverage both the graph topology and graph labels is fundamental to building discriminative node and graph embeddings.

 Ranked #28 on Graph Classification on MUTAG

 Graph Classification

MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization

2 code implementations • 30 Sep 2022

Training graph neural networks (GNNs) on large graphs is complex and extremely time consuming.

 Link Prediction  Node Classification

TC-GNN: Bridging Sparse GNN Computation and Dense Tensor Cores on GPUs

1 code implementation • 3 Dec 2021

The core idea is to reconcile the "Sparse" GNN computation with the high-performance "Dense" TCUs.

 Translation

GNNExplainer: Generating Explanations for Graph Neural Networks

10 code implementations • NeurIPS 2019

We formulate GNNExplainer as an optimization task that maximizes the mutual information between a GNN's prediction and distribution of possible subgraph structures.

 BIG-bench Machine Learning  Explainable artificial intelligence +2