ChaosMining: A Benchmark to Evaluate Post-Hoc Local Attribution Methods in Low SNR Environments

• URL: http://arxiv.org/abs/2406.12150v1
• Date: Mon, 17 Jun 2024 23:39:29 GMT
• Title: ChaosMining: A Benchmark to Evaluate Post-Hoc Local Attribution Methods in Low SNR Environments
• Authors: Ge Shi, Ziwen Kan, Jason Smucny, Ian Davidson,
• Abstract summary: In this study, we examine the efficacy of post-hoc local attribution methods in identifying features with predictive power from irrelevant ones in domains characterized by a low signal-to-noise ratio (SNR) Our experiments highlight its strengths in prediction and feature selection, alongside limitations in scalability.
• Score: 14.284728947052743
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In this study, we examine the efficacy of post-hoc local attribution methods in identifying features with predictive power from irrelevant ones in domains characterized by a low signal-to-noise ratio (SNR), a common scenario in real-world machine learning applications. We developed synthetic datasets encompassing symbolic functional, image, and audio data, incorporating a benchmark on the {\it (Model \(\times\) Attribution\(\times\) Noise Condition)} triplet. By rigorously testing various classic models trained from scratch, we gained valuable insights into the performance of these attribution methods in multiple conditions. Based on these findings, we introduce a novel extension to the notable recursive feature elimination (RFE) algorithm, enhancing its applicability for neural networks. Our experiments highlight its strengths in prediction and feature selection, alongside limitations in scalability. Further details and additional minor findings are included in the appendix, with extensive discussions. The codes and resources are available at \href{https://github.com/geshijoker/ChaosMining/}{URL}.

Related papers

• Noise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimation [53.91958614666386]
  Unsupervised graph representation learning (UGRL) based on graph neural networks (GNNs) We propose a novel UGRL method based on Multi-hop feature Quality Estimation (MQE)
  arXiv  Detail & Related papers  (2024-07-29T12:24:28Z)
• Noisy Self-Training with Synthetic Queries for Dense Retrieval [49.49928764695172]
  We introduce a novel noisy self-training framework combined with synthetic queries. Experimental results show that our method improves consistently over existing methods. Our method is data efficient and outperforms competitive baselines.
  arXiv  Detail & Related papers  (2023-11-27T06:19:50Z)
• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• Nearest Neighbor Guidance for Out-of-Distribution Detection [18.851275688720108]
  We propose Nearest Neighbor Guidance (NNGuide) for detecting out-of-distribution (OOD) samples. NNGuide reduces the overconfidence of OOD samples while preserving the fine-grained capability of the classifier-based score. Our results demonstrate that NNGuide provides a significant performance improvement on the base detection scores.
  arXiv  Detail & Related papers  (2023-09-26T12:40:35Z)
• Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study [51.33182775762785]
  This paper presents an empirical study to build relation extraction systems in low-resource settings. We investigate three schemes to evaluate the performance in low-resource settings: (i) different types of prompt-based methods with few-shot labeled data; (ii) diverse balancing methods to address the long-tailed distribution issue; and (iii) data augmentation technologies and self-training to generate more labeled in-domain data.
  arXiv  Detail & Related papers  (2022-10-19T15:46:37Z)
• Batch-Ensemble Stochastic Neural Networks for Out-of-Distribution Detection [55.028065567756066]
  Out-of-distribution (OOD) detection has recently received much attention from the machine learning community due to its importance in deploying machine learning models in real-world applications. In this paper we propose an uncertainty quantification approach by modelling the distribution of features. We incorporate an efficient ensemble mechanism, namely batch-ensemble, to construct the batch-ensemble neural networks (BE-SNNs) and overcome the feature collapse problem. We show that BE-SNNs yield superior performance on several OOD benchmarks, such as the Two-Moons dataset, the FashionMNIST vs MNIST dataset, FashionM
  arXiv  Detail & Related papers  (2022-06-26T16:00:22Z)
• A Comparative Study of Pre-trained Encoders for Low-Resource Named Entity Recognition [10.0731894715001]
  We introduce an encoder evaluation framework, and use it to compare the performance of state-of-the-art pre-trained representations on the task of low-resource NER. We analyze a wide range of encoders pre-trained with different strategies, model architectures, intermediate-task fine-tuning, and contrastive learning.
  arXiv  Detail & Related papers  (2022-04-11T09:48:26Z)
• Learning Transformer Features for Image Quality Assessment [53.51379676690971]
  We propose a unified IQA framework that utilizes CNN backbone and transformer encoder to extract features. The proposed framework is compatible with both FR and NR modes and allows for a joint training scheme.
  arXiv  Detail & Related papers  (2021-12-01T13:23:00Z)
• A deep learning based surrogate model for stochastic simulators [0.0]
  We propose a deep learning-based surrogate model for simulators. We utilize conditional maximum mean discrepancy (CMMD) as the loss-function. Results obtained indicate the excellent performance of the proposed approach.
  arXiv  Detail & Related papers  (2021-10-24T11:38:47Z)
• Towards Robust Neural Retrieval Models with Synthetic Pre-Training [28.547347789198096]
  We show that synthetic training examples generated using a sequence-to-sequence generator can be effective towards this goal. In our experiments, pre-training with synthetic examples improves retrieval performance in both in-domain and out-of-domain evaluation on five different test sets.
  arXiv  Detail & Related papers  (2021-04-15T22:12:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.