Search Results for author:
Found 13 papers, 8 papers with code
TASER: Temporal Adaptive Sampling for Fast and Accurate Dynamic Graph Representation Learning
Recently, Temporal Graph Neural Networks (TGNNs) have demonstrated state-of-the-art performance in various high-impact applications, including fraud detection and content recommendation.
What Matters to Enhance Traffic Rule Compliance of Imitation Learning for Automated Driving
More research attention has recently been given to end-to-end autonomous driving technologies where the entire driving pipeline is replaced with a single neural network because of its simpler structure and faster inference time.
DistTGL: Distributed Memory-Based Temporal Graph Neural Network Training
Evenworse, the tremendous overhead to synchronize the node memory make it impractical to be deployed to distributed GPU clusters.
Language-Conditioned Imitation Learning with Base Skill Priors under Unstructured Data
In this evaluation, we set up ten tasks and achieved an average 30% improvement in our approach compared to the current state-of-the-art approach, demonstrating a high generalization capability in both simulated environments and the real world.
Penalty-Based Imitation Learning With Cross Semantics Generation Sensor Fusion for Autonomous Driving
In recent times, there has been a growing focus on end-to-end autonomous driving technologies.
Learning from Symmetry: Meta-Reinforcement Learning with Symmetrical Behaviors and Language Instructions
We propose a dual-MDP meta-reinforcement learning method that enables learning new tasks efficiently with symmetrical behaviors and language instructions.
TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs
Our temporal parallel sampler achieves an average of 173x speedup on a multi-core CPU compared with the baselines.
Model-Architecture Co-Design for High Performance Temporal GNN Inference on FPGA
Taking advantage of the model optimizations, we propose a principled hardware architecture using batching, pipelining, and prefetching techniques to further improve the performance.
SeDyT: A General Framework for Multi-Step Event Forecasting via Sequence Modeling on Dynamic Entity Embeddings
SeDyT consists of two components: a Temporal Graph Neural Network that generates dynamic entity embeddings in the past and a sequence model that predicts the entity embeddings in the future.
Accelerating Large Scale Real-Time GNN Inference using Channel Pruning
In this paper, we propose to accelerate GNN inference by pruning the dimensions in each layer with negligible accuracy loss.
Accurate, Efficient and Scalable Training of Graph Neural Networks
For feature propagation within subgraphs, we improve cache utilization and reduce DRAM traffic by data partitioning.
GraphSAINT: Graph Sampling Based Inductive Learning Method
Graph Convolutional Networks (GCNs) are powerful models for learning representations of attributed graphs.
Ranked #1 on
Link Property Prediction
on ogbl-citation2
Accurate, Efficient and Scalable Graph Embedding
However, a major challenge is to reduce the complexity of layered GCNs and make them parallelizable and scalable on very large graphs -- state-of the art techniques are unable to achieve scalability without losing accuracy and efficiency.
