paper-with-me

Papers

On Pitfalls of $\textit{RemOve-And-Retrain}$: Data Processing Inequality Perspective

2023-04-26 · Junhwa Song, Keumgang Cha, Junghoon Seo

Approaches for appraising feature importance approximations, alternatively referred to as attribution methods, have been established across an extensive array of contexts. The development of resilient techniques for performance benchmarking constitutes a critical concern in the sphere of explainable deep learning. This study scrutinizes the dependability of the RemOve-And-Retrain (ROAR) procedure, which is prevalently employed for gauging the performance of feature importance estimates. The insights gleaned from our theoretical foundation and empirical investigations reveal that attributions containing lesser information about the decision function may yield superior results in ROAR benchmarks, contradicting the original intent of ROAR. This occurrence is similarly observed in the recently introduced variant RemOve-And-Debias (ROAD), and we posit a persistent pattern of blurriness bias in ROAR attribution metrics. Our findings serve as a warning against indiscriminate use on ROAR metrics. The code is available as open source.

📄 PDF Abstract BibTeX arXiv:2304.13836

Code (1)

sianalytics/roar 공식 구현

Tasks

BenchmarkingFeature Importance

Similar Papers 제목 키워드 기반

Privacy Adhering Machine Un-learning in NLP

2022-12-19 · Vinayshekhar Bannihatti Kumar, Rashmi Gangadharaiah, Dan Roth

Regulations introduced by General Data Protection Regulation (GDPR) in the EU or California Consumer Privacy Act (CCPA) in the US have included provisions on the \textit{right to be forgotten} that mandates industry appl…

Machine UnlearningQQP

AM Flow: Adapters for Temporal Processing in Action Recognition

2024-11-04 · Tanay Agrawal, Abid Ali, Antitza Dantcheva, Francois Bremond

Deep learning models, in particular \textit{image} models, have recently gained generalisability and robustness. %are becoming more general and robust by the day. In this work, we propose to exploit such advances in the …

Action ClassificationAction RecognitionTransfer LearningVideo Classification

Backdoor Attacks against Transfer Learning with Pre-trained Deep Learning Models

2020-01-10 · Shuo Wang, Surya Nepal, Carsten Rudolph, Marthie Grobler 외

Transfer learning provides an effective solution for feasibly and fast customize accurate \textit{Student} models, by transferring the learned knowledge of pre-trained \textit{Teacher} models over large datasets via fine…

Deep LearningElectrocardiography (ECG)Electroencephalogram (EEG)Time Series+2

Can LLMs $\textit{understand}$ Math? -- Exploring the Pitfalls in Mathematical Reasoning

2025-05-21 · Tiasa Singha Roy, Aditeya Baral, Ayush Rajesh Jhaveri, Yusuf Baig

Large language models (LLMs) demonstrate considerable potential in various natural language tasks but face significant challenges in mathematical reasoning, particularly in executing precise, multi-step logic. However, c…

MathMathematical Reasoning

HuggingFace's Transformers: State-of-the-art Natural Language Processing

2019-10-09 · Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond 외

Recent progress in natural language processing has been driven by advances in both model architecture and model pretraining. Transformer architectures have facilitated building higher-capacity models and pretraining has …

Text GenerationTransfer Learning