Graph Domain Adaptation via Theory-Grounded Spectral Regularization

Authors: Yuning You, Tianlong Chen, Zhangyang Wang, Yang Shen

ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental with numerical agreement with extensive real-world experiments: SS and MFR regularizations bring more benefits to the scenarios of node transfer and link transfer, respectively.
Researcher Affiliation Academia Yuning You1, Tianlong Chen2, Zhangyang Wang2, Yang Shen1 1Department of Electrical and Computer Engineering, Texas A&M University 2Department of Electrical and Computer Engineering, University of Texas at Austin
Pseudocode No The paper contains mathematical derivations and equations but no explicit pseudocode or algorithm blocks were found.
Open Source Code Yes Codes are released at https://github.com/Shen-Lab/GDA-SpecReg.
Open Datasets Yes We utilize protein sequences together with freely accessible computational PPIs via whole-genome comparisons (Szklarczyk et al., 2021) to predict experimental PPIs
Dataset Splits Yes In training, we hold out 20% of human PPIs for validation.
Hardware Specification Yes Experiments are distributed on computer clusters with Tesla K80 GPU (11 GB memory) and NVIDIA A100 GPU (40 GB memory).
Software Dependencies No The paper mentions software components like 'Sinkhorn Transformer', 'GIN', 'PyTorch APIs', and 'MATLAB code' but does not specify their version numbers.
Experiment Setup Yes We train with convergence assured for 500 epochs with learning rate 0.0001, hidden dimension 256 and batch size 128 which is sampled by random walk, optimized by Adam optimizer.