Models | Generator | Implementation | Test | Design inspired by |
---|---|---|---|---|
Transformer |
❌ | ✅ | ✅ | 1, 4 |
OptionalTransformer |
❌ | ✅ | ✅ | 1, 4 |
MaskedTransformer |
❌ | 🛠️ | ❌ | |
GigaGenerator |
✅ | ✅ | ✅ | 5, 6 |
Models | Algorithm | Implementation | Test | Design inspired by |
---|---|---|---|---|
Discriminator |
DeepSets | ✅ | ✅ | 2, 3 |
PairwiseDiscriminator |
DeepSets | ✅ | ✅ | 2, 3 |
GNNDiscriminator |
GNN | 🛠️ | ❌ | |
GigaDiscriminator |
Transformer | ✅ | ✅ | 5, 6, 7 |
- A. Vaswani et al., "Attention Is All You Need", arXiv:1706.03762
- The ATLAS Collaboration, "Deep Sets based Neural Networks for Impact Parameter Flavour Tagging in ATLAS", ATL-PHYS-PUB-2020-014
- M. Zaheer et al., "Deep Sets", arXiv:1703.06114
- L. Liu et al., "Understanding the Difficulty of Training Transformers", arXiv:2004.08249
- M. Kang et al., "Scaling up GANs for Text-to-Image Synthesis", arXiv:2303.05511
- K. Lee et al., "ViTGAN: Training GANs with Vision Transformers", arXiv:2107.04589
- H. Kim, G. Papamakarios and A. Mnih, "The Lipschitz Constant of Self-Attention", arXiv:2006.04710
Transformer implementation freely inspired by the TensorFlow tutorial Neural machine translation with a Transformer and Keras and the Keras tutorial Image classification with Vision Transformer.