Deep neural networks have significantly contributed to the success in predictive accuracy for classification tasks. However, they tend to make over-confident predictions in real-world settings, where domain shifting and out-of-distribution (OOD) examples exist. Most research on uncertainty estimation focuses on computer vision because it provides visual validation on uncertainty quality. However, few have been presented in the natural language process domain. Unlike Bayesian methods that indirectly infer uncertainty through weight uncertainties, current evidential uncertainty-based methods explicitly model the uncertainty of class probabilities through subjective opinions. They further consider inherent uncertainty in data with different root causes, vacuity (i.e., uncertainty due to a lack of evidence) and dissonance (i.e., uncertainty due to conflicting evidence). In our paper, we firstly apply evidential uncertainty in OOD detection for text classification tasks. We propose an inexpensive framework that adopts both auxiliary outliers and pseudo off-manifold samples to train the model with prior knowledge of a certain class, which has high vacuity for OOD samples. Extensive empirical experiments demonstrate that our model based on evidential uncertainty outperforms other counterparts for detecting OOD examples. Our approach can be easily deployed to traditional recurrent neural networks and fine-tuned pre-trained transformers.

7
下载
关闭预览

相关内容

文本分类(Text Classification)任务是根据给定文档的内容或主题,自动分配预先定义的类别标签。

Algorithmic fairness has aroused considerable interests in data mining and machine learning communities recently. So far the existing research has been mostly focusing on the development of quantitative metrics to measure algorithm disparities across different protected groups, and approaches for adjusting the algorithm output to reduce such disparities. In this paper, we propose to study the problem of identification of the source of model disparities. Unlike existing interpretation methods which typically learn feature importance, we consider the causal relationships among feature variables and propose a novel framework to decompose the disparity into the sum of contributions from fairness-aware causal paths, which are paths linking the sensitive attribute and the final predictions, on the graph. We also consider the scenario when the directions on certain edges within those paths cannot be determined. Our framework is also model agnostic and applicable to a variety of quantitative disparity measures. Empirical evaluations on both synthetic and real-world data sets are provided to show that our method can provide precise and comprehensive explanations to the model disparities.

0
4
下载
预览

Due to their increasing spread, confidence in neural network predictions became more and more important. However, basic neural networks do not deliver certainty estimates or suffer from over or under confidence. Many researchers have been working on understanding and quantifying uncertainty in a neural network's prediction. As a result, different types and sources of uncertainty have been identified and a variety of approaches to measure and quantify uncertainty in neural networks have been proposed. This work gives a comprehensive overview of uncertainty estimation in neural networks, reviews recent advances in the field, highlights current challenges, and identifies potential research opportunities. It is intended to give anyone interested in uncertainty estimation in neural networks a broad overview and introduction, without presupposing prior knowledge in this field. A comprehensive introduction to the most crucial sources of uncertainty is given and their separation into reducible model uncertainty and not reducible data uncertainty is presented. The modeling of these uncertainties based on deterministic neural networks, Bayesian neural networks, ensemble of neural networks, and test-time data augmentation approaches is introduced and different branches of these fields as well as the latest developments are discussed. For a practical application, we discuss different measures of uncertainty, approaches for the calibration of neural networks and give an overview of existing baselines and implementations. Different examples from the wide spectrum of challenges in different fields give an idea of the needs and challenges regarding uncertainties in practical applications. Additionally, the practical limitations of current methods for mission- and safety-critical real world applications are discussed and an outlook on the next steps towards a broader usage of such methods is given.

0
13
下载
预览

Invariant approaches have been remarkably successful in tackling the problem of domain generalization, where the objective is to perform inference on data distributions different from those used in training. In our work, we investigate whether it is possible to leverage domain information from the unseen test samples themselves. We propose a domain-adaptive approach consisting of two steps: a) we first learn a discriminative domain embedding from unsupervised training examples, and b) use this domain embedding as supplementary information to build a domain-adaptive model, that takes both the input as well as its domain into account while making predictions. For unseen domains, our method simply uses few unlabelled test examples to construct the domain embedding. This enables adaptive classification on any unseen domain. Our approach achieves state-of-the-art performance on various domain generalization benchmarks. In addition, we introduce the first real-world, large-scale domain generalization benchmark, Geo-YFCC, containing 1.1M samples over 40 training, 7 validation, and 15 test domains, orders of magnitude larger than prior work. We show that the existing approaches either do not scale to this dataset or underperform compared to the simple baseline of training a model on the union of data from all training domains. In contrast, our approach achieves a significant improvement.

0
5
下载
预览

This paper focuses on the expected difference in borrower's repayment when there is a change in the lender's credit decisions. Classical estimators overlook the confounding effects and hence the estimation error can be magnificent. As such, we propose another approach to construct the estimators such that the error can be greatly reduced. The proposed estimators are shown to be unbiased, consistent, and robust through a combination of theoretical analysis and numerical testing. Moreover, we compare the power of estimating the causal quantities between the classical estimators and the proposed estimators. The comparison is tested across a wide range of models, including linear regression models, tree-based models, and neural network-based models, under different simulated datasets that exhibit different levels of causality, different degrees of nonlinearity, and different distributional properties. Most importantly, we apply our approaches to a large observational dataset provided by a global technology firm that operates in both the e-commerce and the lending business. We find that the relative reduction of estimation error is strikingly substantial if the causal effects are accounted for correctly.

0
10
下载
预览

The inaccessibility of controlled randomized trials due to inherent constraints in many fields of science has been a fundamental issue in causal inference. In this paper, we focus on distinguishing the cause from effect in the bivariate setting under limited observational data. Based on recent developments in meta learning as well as in causal inference, we introduce a novel generative model that allows distinguishing cause and effect in the small data setting. Using a learnt task variable that contains distributional information of each dataset, we propose an end-to-end algorithm that makes use of similar training datasets at test time. We demonstrate our method on various synthetic as well as real-world data and show that it is able to maintain high accuracy in detecting directions across varying dataset sizes.

0
3
下载
预览

Although pretrained Transformers such as BERT achieve high accuracy on in-distribution examples, do they generalize to new distributions? We systematically measure out-of-distribution (OOD) generalization for various NLP tasks by constructing a new robustness benchmark with realistic distribution shifts. We measure the generalization of previous models including bag-of-words models, ConvNets, and LSTMs, and we show that pretrained Transformers' performance declines are substantially smaller. Pretrained transformers are also more effective at detecting anomalous or OOD examples, while many previous models are frequently worse than chance. We examine which factors affect robustness, finding that larger models are not necessarily more robust, distillation can be harmful, and more diverse pretraining data can enhance robustness. Finally, we show where future work can improve OOD robustness.

0
5
下载
预览

In information retrieval (IR) and related tasks, term weighting approaches typically consider the frequency of the term in the document and in the collection in order to compute a score reflecting the importance of the term for the document. In tasks characterized by the presence of training data (such as text classification) it seems logical that the term weighting function should take into account the distribution (as estimated from training data) of the term across the classes of interest. Although `supervised term weighting' approaches that use this intuition have been described before, they have failed to show consistent improvements. In this article we analyse the possible reasons for this failure, and call consolidated assumptions into question. Following this criticism we propose a novel supervised term weighting approach that, instead of relying on any predefined formula, learns a term weighting function optimised on the training set of interest; we dub this approach \emph{Learning to Weight} (LTW). The experiments that we run on several well-known benchmarks, and using different learning methods, show that our method outperforms previous term weighting approaches in text classification.

0
8
下载
预览

Embedding models for deterministic Knowledge Graphs (KG) have been extensively studied, with the purpose of capturing latent semantic relations between entities and incorporating the structured knowledge into machine learning. However, there are many KGs that model uncertain knowledge, which typically model the inherent uncertainty of relations facts with a confidence score, and embedding such uncertain knowledge represents an unresolved challenge. The capturing of uncertain knowledge will benefit many knowledge-driven applications such as question answering and semantic search by providing more natural characterization of the knowledge. In this paper, we propose a novel uncertain KG embedding model UKGE, which aims to preserve both structural and uncertainty information of relation facts in the embedding space. Unlike previous models that characterize relation facts with binary classification techniques, UKGE learns embeddings according to the confidence scores of uncertain relation facts. To further enhance the precision of UKGE, we also introduce probabilistic soft logic to infer confidence scores for unseen relation facts during training. We propose and evaluate two variants of UKGE based on different learning objectives. Experiments are conducted on three real-world uncertain KGs via three tasks, i.e. confidence prediction, relation fact ranking, and relation fact classification. UKGE shows effectiveness in capturing uncertain knowledge by achieving promising results on these tasks, and consistently outperforms baselines on these tasks.

0
3
下载
预览

We study few-shot learning in natural language domains. Compared to many existing works that apply either metric-based or optimization-based meta-learning to image domain with low inter-task variance, we consider a more realistic setting, where tasks are diverse. However, it imposes tremendous difficulties to existing state-of-the-art metric-based algorithms since a single metric is insufficient to capture complex task variations in natural language domain. To alleviate the problem, we propose an adaptive metric learning approach that automatically determines the best weighted combination from a set of metrics obtained from meta-training tasks for a newly seen few-shot task. Extensive quantitative evaluations on real-world sentiment analysis and dialog intent classification datasets demonstrate that the proposed method performs favorably against state-of-the-art few shot learning algorithms in terms of predictive accuracy. We make our code and data available for further study.

0
6
下载
预览

Machine translation is a popular test bed for research in neural sequence-to-sequence models but despite much recent research, there is still a lack of understanding of these models. Practitioners report performance degradation with large beams, the under-estimation of rare words and a lack of diversity in the final translations. Our study relates some of these issues to the inherent uncertainty of the task, due to the existence of multiple valid translations for a single source sentence, and to the extrinsic uncertainty caused by noisy training data. We propose tools and metrics to assess how uncertainty in the data is captured by the model distribution and how it affects search strategies that generate translations. Our results show that search works remarkably well but that the models tend to spread too much probability mass over the hypothesis space. Next, we propose tools to assess model calibration and show how to easily fix some shortcomings of current models. We release both code and multiple human reference translations for two popular benchmarks.

0
5
下载
预览
小贴士
相关论文
Weishen Pan,Sen Cui,Jiang Bian,Changshui Zhang,Fei Wang
4+阅读 · 8月11日
Jakob Gawlikowski,Cedrique Rovile Njieutcheu Tassi,Mohsin Ali,Jongseok Lee,Matthias Humt,Jianxiang Feng,Anna Kruspe,Rudolph Triebel,Peter Jung,Ribana Roscher,Muhammad Shahzad,Wen Yang,Richard Bamler,Xiao Xiang Zhu
13+阅读 · 7月7日
Abhimanyu Dubey,Vignesh Ramanathan,Alex Pentland,Dhruv Mahajan
5+阅读 · 3月30日
Yiyan Huang,Cheuk Hang Leung,Xing Yan,Qi Wu,Nanbo Peng,Dongdong Wang,Zhixiang Huang
10+阅读 · 2020年12月17日
Meta Learning for Causal Direction
Jean-Francois Ton,Dino Sejdinovic,Kenji Fukumizu
3+阅读 · 2020年7月6日
Dan Hendrycks,Xiaoyuan Liu,Eric Wallace,Adam Dziedzic,Rishabh Krishnan,Dawn Song
5+阅读 · 2020年4月13日
Learning to Weight for Text Classification
Alejandro Moreo Fernández,Andrea Esuli,Fabrizio Sebastiani
8+阅读 · 2019年3月28日
Xuelu Chen,Muhao Chen,Weijia Shi,Yizhou Sun,Carlo Zaniolo
3+阅读 · 2018年11月26日
Mo Yu,Xiaoxiao Guo,Jinfeng Yi,Shiyu Chang,Saloni Potdar,Yu Cheng,Gerald Tesauro,Haoyu Wang,Bowen Zhou
6+阅读 · 2018年5月19日
Myle Ott,Michael Auli,David Granger,Marc'Aurelio Ranzato
5+阅读 · 2018年2月28日
相关VIP内容
专知会员服务
14+阅读 · 7月17日
专知会员服务
97+阅读 · 2020年9月7日
专知会员服务
62+阅读 · 2020年5月31日
因果图,Causal Graphs,52页ppt
专知会员服务
141+阅读 · 2020年4月19日
Keras François Chollet 《Deep Learning with Python 》, 386页pdf
专知会员服务
60+阅读 · 2019年10月12日
2019年机器学习框架回顾
专知会员服务
25+阅读 · 2019年10月11日
机器学习入门的经验与建议
专知会员服务
42+阅读 · 2019年10月10日
相关资讯
异常检测(Anomaly Detection)综述
极市平台
8+阅读 · 2020年10月24日
Multi-Task Learning的几篇综述文章
深度学习自然语言处理
7+阅读 · 2020年6月15日
【论文笔记】通俗理解少样本文本分类 (Few-Shot Text Classification) (1)
深度学习自然语言处理
6+阅读 · 2020年4月8日
Hierarchically Structured Meta-learning
CreateAMind
10+阅读 · 2019年5月22日
Transferring Knowledge across Learning Processes
CreateAMind
7+阅读 · 2019年5月18日
无监督元学习表示学习
CreateAMind
20+阅读 · 2019年1月4日
Unsupervised Learning via Meta-Learning
CreateAMind
29+阅读 · 2019年1月3日
disentangled-representation-papers
CreateAMind
23+阅读 · 2018年9月12日
Hierarchical Disentangled Representations
CreateAMind
3+阅读 · 2018年4月15日
【学习】Hierarchical Softmax
机器学习研究会
3+阅读 · 2017年8月6日
Top