Multi-Task Processes

Authors: Donggyun Kim, Seongwoong Cho, Wonkwang Lee, Seunghoon Hong

ICLR 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments demonstrate that MTNPs can successfully model multiple tasks jointly by discovering and exploiting their correlations in various real-world data such as time series of weather attributes and pixel-aligned visual modalities.
Researcher Affiliation Academia Donggyun Kim, Seongwoong Cho, Wonkwang Lee, Seunghoon Hong School of Computing, KAIST {kdgyun425, seongwoongjo, wonkwang.lee, seunghoon.hong}@kaist.ac.kr
Pseudocode No The paper describes the neural network architecture and process but does not include a formal pseudocode or algorithm block.
Open Source Code Yes We release our code at https://github.com/Git Gyun/multi_task_neural_processes.
Open Datasets Yes We use 30,000 RGB images from Celeb A HQ dataset (Liu et al., 2015) for RGB task and the corresponding semantic segmentation masks among 19 semantic classes from Celeb A Mask-HQ dataset (Lee et al., 2020) for Segment task.
Dataset Splits Yes We split the 1,000 functions into 800 training, 100 validation, and 100 test sets of four correlated tasks.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory) used for running experiments were mentioned in the paper.
Software Dependencies No The paper mentions software like Deeplab V3+ but does not provide specific version numbers for software components to ensure reproducibility.
Experiment Setup Yes For all three models, we schedule learning rate lr by lr = base_lr 10000.5 min(n_iters 1, 000 1.5, n_iters 0.5), where n_iters is the number of total iterations and base_lr is the base learning rate. We also introduce beta coefficient on the ELBO objective following Higgins et al. (2017), which is multiplied by each KL term. The beta coefficient is scheduled to be linearly increased from 0 to 1 during the first 10000 iters, then fixed to 1. We summarize the training hyper-parameters of models used in the experiments in Table 7.