To the best of our knowledge, Tikick is the first learning-based AI system that can take over the multi-agent Google Research Football full game, while previous work could either control a single agent or experiment on toy academic scenarios.
In this paper, we propose GraphVite, a high-performance CPU-GPU hybrid system for training node embeddings, by co-optimizing the algorithm and the system.
Ranked #1 on Node Classification on YouTube
Recent deep learning (DL) models have moved beyond static network architectures to dynamic ones, handling data where the network structure changes every example, such as sequences of variable lengths, trees, and graphs.
We study the problem of conditional generative modeling based on designated semantics or structures.
We show that Poseidon enables Caffe and TensorFlow to achieve 15. 5x speed-up on 16 single-GPU machines, even with limited bandwidth (10GbE) and the challenging VGG19-22K network for image classification.