Towards Robust Active Feature Acquisition

• URL: http://arxiv.org/abs/2107.04163v1
• Date: Fri, 9 Jul 2021 01:06:13 GMT
• Title: Towards Robust Active Feature Acquisition
• Authors: Yang Li, Siyuan Shan, Qin Liu, Junier B. Oliva
• Abstract summary: Active feature acquisition (AFA) models deal with a small set of candidate features and have difficulty scaling to a large feature space. We propose several techniques to advance the current AFA approaches. Our framework can easily handle a large number of features using a hierarchical acquisition policy and is more robust to OOD inputs with the help of an OOD detector for partially observed data.
• Score: 14.785570635390744
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Truly intelligent systems are expected to make critical decisions with incomplete and uncertain data. Active feature acquisition (AFA), where features are sequentially acquired to improve the prediction, is a step towards this goal. However, current AFA models all deal with a small set of candidate features and have difficulty scaling to a large feature space. Moreover, they are ignorant about the valid domains where they can predict confidently, thus they can be vulnerable to out-of-distribution (OOD) inputs. In order to remedy these deficiencies and bring AFA models closer to practical use, we propose several techniques to advance the current AFA approaches. Our framework can easily handle a large number of features using a hierarchical acquisition policy and is more robust to OOD inputs with the help of an OOD detector for partially observed data. Extensive experiments demonstrate the efficacy of our framework over strong baselines.

Related papers

• Inverse-RLignment: Inverse Reinforcement Learning from Demonstrations for LLM Alignment [62.05713042908654]
  We introduce Alignment from Demonstrations (AfD), a novel approach leveraging high-quality demonstration data to overcome these challenges. We formalize AfD within a sequential decision-making framework, highlighting its unique challenge of missing reward signals. Practically, we propose a computationally efficient algorithm that extrapolates over a tailored reward model for AfD.
  arXiv  Detail & Related papers  (2024-05-24T15:13:53Z)
• Evaluation of Active Feature Acquisition Methods for Time-varying Feature Settings [6.082810456767599]
  Machine learning methods often assume that input features are available at no cost. In domains like healthcare, where acquiring features could be expensive harmful, it is necessary to balance a features acquisition against its predictive positivity. We present a problem of active feature acquisition performance evaluation (AFAPE)
  arXiv  Detail & Related papers  (2023-12-03T23:08:29Z)
• Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [52.06176253457522]
  We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
  arXiv  Detail & Related papers  (2023-08-18T13:13:09Z)
• Acquisition Conditioned Oracle for Nongreedy Active Feature Acquisition [16.350351668269415]
  We develop methodology for active feature acquisition (AFA) We show that we can bypass many challenges with a novel, nonparametric oracle based approach.
  arXiv  Detail & Related papers  (2023-02-27T17:02:11Z)
• Improving the Adversarial Robustness of NLP Models by Information Bottleneck [112.44039792098579]
  Non-robust features can be easily manipulated by adversaries to fool NLP models. In this study, we explore the feasibility of capturing task-specific robust features, while eliminating the non-robust ones by using the information bottleneck theory. We show that the models trained with our information bottleneck-based method are able to achieve a significant improvement in robust accuracy.
  arXiv  Detail & Related papers  (2022-06-11T12:12:20Z)
• ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection [19.61846393392849]
  ProtoInfoMax is a new architecture that extends Prototypical Networks to simultaneously process In-Domain (ID) and OOD sentences. We show that our proposed method can substantially improve performance up to 20% for OOD detection in low resource settings.
  arXiv  Detail & Related papers  (2021-08-27T11:55:34Z)
• Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU [70.44344060176952]
  Intent classification is a major task in spoken language understanding (SLU) Recent works have shown that using extra data and labels can improve the OOD detection performance. This paper proposes to train a model with only IND data while supporting both IND intent classification and OOD detection.
  arXiv  Detail & Related papers  (2021-06-28T08:27:38Z)
• Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational Profiles [13.31639740011618]
  We present a model-agnostic reliability assessment method for Deep Learning (DL) classifiers. We partition the input space into small cells and then "assemble" their robustness (to the ground truth) according to the operational profile (OP) of a given application. Reliability estimates in terms of the probability of misclassification per input (pmi) can be derived together with confidence levels.
  arXiv  Detail & Related papers  (2021-06-02T16:10:46Z)
• Progressive Self-Guided Loss for Salient Object Detection [102.35488902433896]
  We present a progressive self-guided loss function to facilitate deep learning-based salient object detection in images. Our framework takes advantage of adaptively aggregated multi-scale features to locate and detect salient objects effectively.
  arXiv  Detail & Related papers  (2021-01-07T07:33:38Z)
• Active Feature Acquisition with Generative Surrogate Models [11.655069211977464]
  In this work, we consider models that perform active feature acquisition (AFA) and query the environment for unobserved features. Our work reformulates the Markov decision process (MDP) that underlies the AFA problem as a generative modeling task. We propose learning a generative surrogate model ( GSM) that captures the dependencies among input features to assess potential information gain from acquisitions.
  arXiv  Detail & Related papers  (2020-10-06T02:10:06Z)
• Accurate and Robust Feature Importance Estimation under Distribution Shifts [49.58991359544005]
  PRoFILE is a novel feature importance estimation method. We show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.
  arXiv  Detail & Related papers  (2020-09-30T05:29:01Z)

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.