Multi-Task Learning via Time-Aware Neural ODE
Authors: Feiyang Ye, Xuehao Wang, Yu Zhang, Ivor W. Tsang
IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments show that the proposed NORMAL model outperforms stateof-the-art MTL models. In this section, we empirically evaluate the proposed NORMAL method on four benchmark datasets, including Office31 [Saenko et al., 2010], Office-Home [Venkateswara et al., 2017], NYUv2 [Silberman et al., 2012], and Celeb A [Liu et al., 2015]. |
| Researcher Affiliation | Academia | 1 Department of Computer Science and Engineering, Southern University of Science and Technology 2 Australian Artificial Intelligence Institute, University of Technology Sydney 3 Centre for Frontier AI Research, A*STAR 4 Institute of High Performance Computing, A*STAR 5 Peng Cheng Laboratory |
| Pseudocode | Yes | Algorithm 1 The NORMAL model. Input: training data and learning rates µ, η Output: Task-shared parameters θ, φ, task-specific parameters {ϕi}, {pi} |
| Open Source Code | No | The paper does not provide an explicit statement about releasing the source code or a link to a code repository. |
| Open Datasets | Yes | In this section, we empirically evaluate the proposed NORMAL method on four benchmark datasets, including Office31 [Saenko et al., 2010], Office-Home [Venkateswara et al., 2017], NYUv2 [Silberman et al., 2012], and Celeb A [Liu et al., 2015]. |
| Dataset Splits | Yes | The NYUv2 dataset [Silberman et al., 2012] ... It contains 1,449 images with ground truth, where 795 images are for training and 654 images are for validation. |
| Hardware Specification | Yes | All experiments are performed on a single NVIDIA Ge Force RTX 3090 GPU. |
| Software Dependencies | No | The paper mentions software components like 'Res Net-18 network', 'Euler s method as the ODE solver', 'Deep Lab V3+ architecture', and 'HBNODE', but does not provide specific version numbers for any software dependencies (e.g., Python version, PyTorch/TensorFlow version, or other library versions). |
| Experiment Setup | Yes | On both datasets, we use a Res Net-18 network pre-trained on the Image Net dataset as fθ, the Euler s method as the ODE solver, and a task-specific fully connected layer as the corresponding head for each task. Initial Velocity: FC Leaky Re LU FC ODE Function: FC Leaky Re LU FC All the fully connected (FC) layers of both functions have a dimension of 512 for inputs and outputs. The numbers of the input channel and output channel of the convolution layers of both functions are set to 512, the size of the kernel is 1, the stride size is 1, and the padding is 0. |