paper-with-me

Papers

CAFE: Conflict-Aware Feature-wise Explanations

2023-10-31 · Adam Dejl, Hamed Ayoobi, Matthew Williams, Francesca Toni

Feature attribution methods are widely used to explain neural models by determining the influence of individual input features on the models' outputs. We propose a novel feature attribution method, CAFE (Conflict-Aware Feature-wise Explanations), that addresses three limitations of the existing methods: their disregard for the impact of conflicting features, their lack of consideration for the influence of bias terms, and an overly high sensitivity to local variations in the underpinning activation functions. Unlike other methods, CAFE provides safeguards against overestimating the effects of neuron inputs and separately traces positive and negative influences of input features and biases, resulting in enhanced robustness and increased ability to surface feature conflicts. We show experimentally that CAFE is better able to identify conflicting features on synthetic tabular data and exhibits the best overall fidelity on several real-world tabular datasets, while being highly computationally efficient.

📄 PDF Abstract BibTeX arXiv:2310.20363

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

CAFEDistill: Learning Personalized and Dynamic Models through Federated Early-Exit Network Distillation

2026-01-15 · Boyi Liu, Zimu Zhou, Yongxin Tong arxiv

Personalized Federated Learning (PFL) enables collaboratively model training on decentralized, heterogeneous data while tailoring them to each client's unique distribution. However, existing PFL methods produce static mo…

Personalized Federated Learning

CAFE-GB: Scalable and Stable Feature Selection for Malware Detection via Chunk-wise Aggregated Gradient Boosting

2026-01-22 · Ajvad Haneef K, Karan Kuwar Singh, Madhu Kumar S D arxiv

High-dimensional malware datasets often exhibit feature redundancy, instability, and scalability limitations, which hinder the effectiveness and interpretability of machine learning-based malware detection systems. Altho…

Feature ImportanceMalware Detection

Causal Interpretation of Sparse Autoencoder Features in Vision

2025-08-31 · Sangyu Han, Yearim Kim, Nojun Kwak arxiv

Understanding what sparse auto-encoder (SAE) features in vision transformers truly represent is usually done by inspecting the patches where a feature's activation is highest. However, self-attention mixes information ac…

Content-Aware Frequency Encoding for Implicit Neural Representations with Fourier-Chebyshev Features

2026-03-01 · Junbo Ke, Yangyang Xu, You-Wei Wen, Chao Wang arxiv

Implicit Neural Representations (INRs) have emerged as a powerful paradigm for various signal processing tasks, but their inherent spectral bias limits the ability to capture high-frequency details. Existing methods part…

ScaFE: Data-Efficient Scar Classification with LLM-Generated Clinical Feature Programs

2026-07-30 · Ruman Wang, Hangting Ye arxiv

Classifying pathological scars from clinical photographs requires distinguishing keloids from hypertrophic scars despite limited expert-labeled data and substantial acquisition variation across hospitals. End-to-end imag…

Medical Image ClassificationFeature EngineeringClinical Knowledge