Gyrogroup Batch Normalization
Authors: Ziheng Chen, Yue Song, Xiaojun Wu, Nicu Sebe
ICLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on the Grassmannian and hyperbolic networks demonstrate the effectiveness of our Gyro BN. The code is available at https://github.com/Git ZH-Chen/Gyro BN.git. [...] 7 EXPERIMENTS Our Gyro BN layers are model-agnostic and can be seamlessly integrated into any network operating over the gyrospaces listed in Tab. 2. This section evaluates the effectiveness of our Gyro BN on Grassmannian and hyperbolic neural networks. |
| Researcher Affiliation | Academia | Ziheng Chen1 , Yue Song1, Xiao-Jun Wu2 & Nicu Sebe1 1 University of Trento, 2 Jiangnan University |
| Pseudocode | Yes | Algorithm 1: Gyrogroup Batch Normalization (Gyro BN) Require : batch of activations {P1...N M}, small positive constant ϵ, and momentum η [0, 1], running mean Mr, running variance v2 r, biasing parameter B M, scaling parameter s R. Return :normalized batch { P1...N M} |
| Open Source Code | Yes | The code is available at https://github.com/Git ZH-Chen/Gyro BN.git. |
| Open Datasets | Yes | Following Nguyen & Yang (2023), we evaluate our method on skeleton-based action recognition tasks, including the HDM05 (Müller et al., 2007), NTU60 (Shahroudy et al., 2016), and NTU120 (Liu et al., 2019) datasets, focusing on mutual actions for NTU60 and NTU120. [...] we validate our hyperbolic Gyro BN, referred to as Gyro BN-H, on the Hyperbolic Neural Network (HNN) (Ganea et al., 2018) backbone for the link prediction task using the Cora (Sen et al., 2008), Disease (Anderson & May, 1991), Airport (Zhang & Chen, 2018), and Pubmed (Namata et al., 2012) datasets. |
| Dataset Splits | Yes | The 5-fold results are presented in Tab. 3. [...] Tab. 5 reports 5-fold average results of testing AUC on the four datasets. [...] For the Grassmannian experiments: NTU60 (Shahroudy et al., 2016). We use mutual actions and follow the cross-view protocol (Shahroudy et al., 2016). NTU120 (Liu et al., 2019). We use mutual actions and follow the cross-setup protocol (Liu et al., 2019). |
| Hardware Specification | Yes | All experiments except the ones on the Pubmed dataset use an Intel Core i9-7960X CPU with 32GB RAM and an NVIDIA Ge Force RTX 2080 Ti GPU. The experiments on the Pubmed dataset are conducted on a single NVIDIA Quadro RTX A6000 48GB GPU. |
| Software Dependencies | No | The paper mentions PyTorch (Paszke et al., 2019) and Adam optimizer (Kingma, 2014) but does not provide specific version numbers for the software libraries used (e.g., Python 3.x, PyTorch 1.x, CUDA 11.x). |
| Experiment Setup | Yes | In all experiments, we use an SGD optimizer with a learning rate of 5e-2 and zero weight decay. The batch size is 30, and training epochs are 400, 200, and 200 for the HDM05, NTU60, and NTU120 datasets. [...] We use the Adam optimizer (Kingma, 2014), with a learning rate of 1e 2 and a weight decay of 1e 3, except for the Cora dataset, where the weight decay is set to 0. |