Jeremiah Liu
Research Areas
Authored Publications
Sort By
Pushing the Accuracy-Group Robustness Tradeoff Frontier with Introspective Self-play
Dj Dvijotham
Jihyeon Lee
Martin Strobel
Quan Yuan
ICLR'23 (2023) (to appear)
Preview abstract
Improving the accuracy-fairness frontier of deep neural network (DNN) models is an important problem. Uncertainty-based active learning active learning (AL)can potentially improve the frontier by preferentially sampling underrepresented subgroups to create a more balanced training dataset. However, the quality of uncertainty estimates from modern DNNs tend to degrade in the presence of spurious correlations and dataset bias, compromising the effectiveness of AL for sampling tail groups. In this work, we propose Introspective Self-play (ISP), a simple approach to improve the uncertainty estimation of a deep neural network under dataset bias, by adding an auxiliary introspection task requiring a model to predict the bias for each data point in addition to the label. We show that ISP provably improves the bias-awareness of the model representation and the resulting uncertainty estimates. On two real-world tabular and language tasks, ISP serves as a simple “plug-in” for AL model training, consistently improving both the tail-group sampling rate and the final accuracy-fairness trade-off frontier of popular AL methods.
View details
Plex: Towards Reliability using Pretrained Large Model Extensions
Du Phan
Mark Patrick Collier
Zi Wang
Zelda Mariet
Clara Huiyi Hu
Neil Band
Tim G. J. Rudner
Karan Singhal
Joost van Amersfoort
Andreas Christian Kirsch
Rodolphe Jenatton
Honglin Yuan
Kelly Buchanan
Yarin Gal
ICML 2022 Pre-training Workshop (2022)
Preview abstract
A recent trend in artificial intelligence (AI) is the use of pretrained models for language and vision tasks, which has achieved extraordinary performance but also puzzling failures. Examining tasks that probe the model’s abilities in diverse ways is therefore critical to the field. In this paper, we explore the \emph{reliability} of models, where we define a reliable model as one that not only achieves strong predictive performance but also performs well consistently over many decision-making tasks such as uncertainty (e.g., selective prediction, open set recognition), robust generalization (e.g., accuracy and scoring rules such as log-likelihood on in- and out-of-distribution datasets), and adaptation (e.g., active learning, few-shot learning). We devise 11 types of tasks over 36 datasets in order to evaluate different aspects of reliability on both vision and language domains. To improve reliability, we developed ViT-Plex and T5-Plex, \emph{p}retrained \emph{l}arge-model \emph{ex}tensions (henceforth abbreviated as \emph{plex}) for vision and language modalities. Plex greatly improves the state-of-the-art across tasks, and as a pretrained model Plex unifies the traditional protocol of designing and tuning one model for each reliability task. We demonstrate scaling effects over model sizes and pretraining dataset sizes up to 4 billion examples. We also demonstrate Plex’s capabilities on new tasks including zero-shot open set recognition, few-shot uncertainty, and uncertainty in conversational language understanding.
View details
A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness
Shreyas Padhy
Zi Lin
Yeming Wen
Ghassen Jerfel
Journal of Machine Learning Research (2022)
Preview abstract
Accurate uncertainty quantification is a major challenge in deep learning, as neural networks can make overconfident errors and assign high confidence predictions to out-of-distribution (OOD) inputs. The most popular approaches to estimate predictive uncertainty in deep learning are methods that combine predictions from multiple neural networks, such as Bayesian neural networks (BNNs) and deep ensembles. However their practicality in real-time, industrial-scale applications are limited due to the high memory and computational cost. Furthermore, ensembles and BNNs do not necessarily fix all the issues with the underlying member networks. In this work, we study principled approaches to improve uncertainty property of a single network, based on a single, deterministic representation. By formalizing the uncertainty quantification as a minimax learning problem, we first identify distance awareness, i.e., the model's ability to quantify the distance of a testing example from the training data, as a necessary condition for a DNN to achieve high-quality (i.e., minimax optimal) uncertainty estimation. We then propose Spectral-normalized Neural Gaussian Process (SNGP), a simple method that improves the distance-awareness ability of modern DNNs with two simple changes: (1) applying spectral normalization to hidden weights to enforce bi-Lipschitz smoothness in representations and (2) replacing the last output layer with a Gaussian process layer. On a suite of vision and language understanding benchmarks, SNGP outperforms other single-model approaches in prediction, calibration and out-of-domain detection. Furthermore, SNGP provides complementary benefits to popular techniques such as deep ensembles and data augmentation, making it a simple and scalable building block for probabilistic deep learning. Code is open-sourced at https://github.com/google/uncertainty-baselines.
View details
Training independent subnetworks for robust prediction
Marton Havasi
Rodolphe Jenatton
Stanislav Fort
International Conference on Learning Representations (2021)
Preview abstract
Recent approaches to efficiently ensemble neural networks have shown that strong robustness and uncertainty performance can be achieved with a negligible gain in parameters over the original network. However, these methods still require multiple forward passes for prediction, leading to a significant runtime cost. In this work, we show a surprising result: the benefits of using multiple predictions can be achieved 'for free' under a single model's forward pass. In particular, we show that, using a multi-input multi-output (MIMO) configuration, one can utilize a single model's capacity to train multiple subnetworks that independently learn the task at hand. By ensembling the predictions made by the subnetworks, we improve model robustness without increasing compute. We observe a significant improvement in negative log-likelihood, accuracy, and calibration error on CIFAR10, CIFAR100, ImageNet, and their out-of-distribution variants compared to previous methods.
View details
Preview abstract
The concern of overconfident mis-predictions under distributional shift demands extensive reliability research on Graph Neural Networks used in critical tasks in drug discovery. Here we first introduce CardioTox, a real-world benchmark on drug cardio-toxicity to facilitate such efforts. Our exploratory study shows overconfident mis-predictions are often distant from training data. That leads us to develop distance-aware GNNs: GNN-SNGP. Through evaluation on CardioTox and three established benchmarks, we demonstrate GNN-SNGP's effectiveness in increasing distance-awareness, reducing overconfident mis-predictions and making better calibrated predictions without sacrificing accuracy performance. Our ablation study further reveals the representation learned by GNN-SNGP improves distance-preservation over its base architecture and is one major factor for improvements.
View details
Deep Classifiers with Label Noise Modeling and Distance Awareness
Vincent Fortuin
Mark Patrick Collier
Florian Wenzel
James Urquhart Allingham
Jesse Berent
Rodolphe Jenatton
NeurIPS 2021 Workshop on Bayesian Deep Learning (2021) (to appear)
Preview abstract
Uncertainty estimation in deep learning has recently emerged as a crucial area of interest to advance reliability and robustness of deep learning models, especially in safety-critical applications.
While there have been many proposed methods that either focus on distance-aware model uncertainties for out-of-distribution detection or respectively on input-dependent label uncertainties for in-distribution calibration, combining these two approaches has been less well explored.
In this work, we propose to combine these two ideas to achieve a joint modeling of model (epistemic) and data (aleatoric) uncertainty.
We show that our combined model affords a favorable combination between these two complementary types of uncertainty and thus achieves good performance in-distribution and out-of-distribution on different benchmark datasets.
View details
Preview abstract
Content moderation is often performed by a collaboration between humans and machine learning models. The machine learning models used in this collaboration are typically evaluated using metrics like accuracy or AUROC. However, such metrics do not capture the performance of the combined moderator-model system. Here, we introduce metrics analogous to accuracy and AUC that describe the overall system performance under constraints on human review bandwidth, and that quantify how efficiently and effectively these systems make use of human decision-making. We evaluate the performance of several models using these new metrics as well as existing ones under different review policies (the order in which moderators review comments from the model), finding that simple uncertainty-based review policies outperform traditional toxicity-based ones across a range of human bandwidths. Our results demonstrate the importance of metrics capturing the collaborative nature of the moderator-model system for this task, as well as the utility of uncertainty estimation for the content moderation problem.
View details
Variable Selection with Rigorous Uncertainty Quantification using Bayesian Deep Neural Networks: Posterior Concentration and Bernstein-von Mises Phenomenon
International Conference on Artificial Intelligence and Statistics, PMLR (2021)
Preview abstract
This work establishes on theoretical basis that Bayesian deep neural network is an effective tool for high-dimensional variable selection with rigorous uncertainty quantification. For a properly configured deep Bayesian neural network (BNN), we show that (1) BNN learns the variable importance effectively in high dimension, and its learning rate can sometimes “break” the curse of dimensionality; (2) BNN’s uncertainty quantification for variable importance is rigorous, in the sense that its 95% credible intervals for variable importance indeed covers the truth 95% of the time (i.e. the Bernstein-von Mises (BvM) phenomenon). The theoretic result suggests a simple variable selection algorithm based on the BNN credible intervals. Extensive simulation confirms the theoretical findings and shows the proposed algorithm outperforms existing classic and machine-learning based variable selection methods especially in high dimension.
View details
Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness
Zi Lin
Shreyas Padhy
Advances in Neural Information Processing Systems 33, Curran Associates, Inc. (2020) (to appear)
Preview abstract
Bayesian neural networks (BNN) and Deep Ensembles are principled approaches to estimate the predictive uncertainty of a deep learning model. However their practicality in real-time, industrial-scale applications are limited due to their heavy memory and inference cost. This motivates us to study principled approaches to high-quality uncertainty estimation that require only a single deep neural network (DNN). By formalizing the uncertainty quantification as a minimax learning problem, we first identify \textit{input distance awareness}, i.e., the model’s ability in quantifying the distance of a testing example from the training data in the input space, as a necessary condition for a DNN to achieve high-quality (i.e., minimax optimal) uncertainty estimation. We then propose \textit{Spectral-normalized Gaussian Process} (SNGP), a simple method that improves the distance-awareness ability of modern DNNs, by adding a weight normalization step during training and replacing the activation of the penultimate layer. We visually illustrate the property of the proposed method on two-dimensional datasets, and benchmark its performance against Deep Ensembles and other single-model approaches across both vision and language understanding tasks and on modern architectures (ResNet and BERT). Despite its simplicity, SNGP is competitive with Deep Ensembles in prediction, calibration and out-of-domain detection, and significantly outperforms the other single-model approaches.
View details
Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks
Shreyas Padhy
(2020)
Preview abstract
Accurate estimation of predictive uncertainty in modern neural networks is critical to achieve well calibrated predictions and detect out-of-distribution inputs. The most promising approaches have been predominantly focused on improving model uncertainty (e.g. deep ensembles and Bayesian neural networks) and post-processing techniques for out-of-distribution detection (e.g. ODIN and Mahalanobis distance). However, there has been relatively little investigation into how the parametrization of the probabilities in discriminative classifiers affects the uncertainty estimates, and the dominant method, softmax cross-entropy, results in misleadingly high confidences on out-of-distribution data and under covariate shift. We investigate alternative ways of formulating probabilities using (1) a one-vs-all formulation to capture the notion of “none of the above”, and (2) a distance-based logit representation to encode uncertainty as a function of distance to the training manifold. We show that one-vs-all formulations can match the predictive performance of softmax without incurring any additional training or test-time complexity, and improve calibration on image classification tasks.
View details
