Fully Test-Time Adaptation for Feature Decrement in Tabular Data

Authors: Zi-Jian Cheng, Zi-Yi Jia, Kun-Yang Yu, Zhi Zhou, Lan-Zhe Guo

IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experimental results demonstrate that our proposal significantly improves both performance and robustness in missing feature imputation and adaptation scenarios. Comprehensive experiments on 9 datasets demonstrate that proposed FTTA methods exhibit significant improvements in performance and robustness in feature decrements over 11 comparison models.
Researcher Affiliation Academia 1School of Intelligence Science and Technology, Nanjing University, China 2National Key Laboratory for Novel Software Technology, Nanjing University, China 3School of Artificial Intelligence, Nanjing University, China EMAIL, EMAIL
Pseudocode No The paper describes the methodology for LLM-IMPUTE and ATLLM with textual descriptions and figures (Figure 3: a prompt template, Figure 4: an overview diagram), but it does not contain a clearly labeled pseudocode or algorithm block with structured steps.
Open Source Code No The paper does not contain any explicit statements about releasing source code, nor does it provide a link to a code repository or mention code in supplementary materials.
Open Datasets Yes To effectively simulate feature-decrement scenarios in tabular data, we select a variety of open-source and reliable datasets from Open ML and Kaggle s extensive dataset library. These datasets encompass three primary tasks: binary classification, multi-class classification, and regression, and span a range of fields such as finance and healthcare. A summary of the key attributes of the datasets is provided in Appendix A.
Dataset Splits No The paper mentions using 'training data', 'testing data', and 'validation' in a general sense but does not provide specific details on how the datasets were split, such as percentages, sample counts, or the methodology used for partitioning.
Hardware Specification No The paper does not provide specific details about the hardware used to run the experiments, such as GPU models, CPU types, or memory specifications.
Software Dependencies No The paper mentions 'Llama3-8B, a model released by Meta AI in April 2024' as a specific LLM used. However, it does not provide a reproducible description of ancillary software, such as programming languages, libraries, or other tools with their specific version numbers (e.g., Python, PyTorch, CUDA versions).
Experiment Setup Yes During fine-tuning, the number of epochs is set to 30 to ensure that the model has ample opportunity to learn and converge. The learning rate is set to 1e 5 to prevent overfitting and enable the model to converge effectively.