Author name cluster

Yoav Wald

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

13 papers

2 author rows

TMLR Journal 2025 Journal Article

Between Linear and Sinusoidal: Rethinking the Time Encoder in Dynamic Graph Learning

Hsing-Huan Chung
Shravan S Chaudhari
Xing Han
Yoav Wald
Suchi Saria
Joydeep Ghosh

Dynamic graph learning is essential for applications involving temporal networks and requires effective modeling of temporal relationships. Seminal attention-based models like TGAT and DyGFormer rely on sinusoidal time encoders to capture temporal dependencies between edge events. Prior work justified sinusoidal encodings because their inner products depend on the time spans between events, which are crucial features for modeling inter-event relations. However, sinusoidal encodings inherently lose temporal information due to their many-to-one nature and therefore require high dimensions. In this paper, we rigorously study a simpler alternative: the linear time encoder, which avoids temporal information loss caused by sinusoidal functions and reduces the need for high-dimensional time encoders. We show that the self-attention mechanism can effectively learn to compute time spans between events from linear time encodings and extract relevant temporal patterns. Through extensive experiments on six dynamic graph datasets, we demonstrate that the linear time encoder improves the performance of TGAT and DyGFormer in most cases. Moreover, the linear time encoder can lead to significant savings in model parameters with minimal performance loss. For example, compared to a 100-dimensional sinusoidal time encoder, TGAT with a 2-dimensional linear time encoder saves 43% of parameters and achieves higher average precision on five datasets. While both encoders can be used simultaneously, our study highlights the often-overlooked advantages of linear time features in modern dynamic graph models. These findings can positively impact the design choices of various dynamic graph learning architectures and eventually benefit temporal network applications such as recommender systems, communication networks, and traffic forecasting. The experimental code is available at: https://github.com/hsinghuan/dg-linear-time.git.

PDF Details

ICLR Conference 2025 Conference Paper

Time After Time: Deep-Q Effect Estimation for Interventions on When and What to do

Yoav Wald
Mark Goldstein
Yonathan Efroni
Wouter A. C. van Amsterdam
Rajesh Ranganath

Problems in fields such as healthcare, robotics, and finance requires reasoning about the value both of what decision or action to take and when to take it. The prevailing hope is that artificial intelligence will support such decisions by estimating the causal effect of policies such as how to treat patients or how to allocate resources over time. However, existing methods for estimating the effect of a policy struggle with \emph{irregular time}. They either discretize time, or disregard the effect of timing policies. We present a new deep-Q algorithm that estimates the effect of both when and what to do called Earliest Disagreement Q-Evaluation (EDQ). EDQ makes use of recursion for the Q-function that is compatible with flexible sequence models, such as transformers. EDQ provides accurate estimates under standard assumptions. We validate the approach through experiments on survival time and tumor growth tasks.

Details

TMLR Journal 2024 Journal Article

Nuisances via Negativa: Adjusting for Spurious Correlations via Data Augmentation

Aahlad Manas Puli
Nitish Joshi
Yoav Wald
He He
Rajesh Ranganath

In prediction tasks, there exist features that are related to the label in the same way across different settings for that task; these are semantic features or semantics. Features with vary- ing relationships to the label are nuisances. For example, in detecting cows from natural images, the shape of the head is semantic, but because images of cows often have grass back- grounds but not always, the background is a nuisance. Models that exploit nuisance-label relationships face performance degradation when these relationships change. Building mod- els robust to such changes requires additional knowledge beyond samples of the features and labels. For example, existing work uses annotations of nuisances or assumes erm-trained models depend on nuisances. Approaches to integrate new kinds of additional knowledge enlarge the settings where robust models can be built. We develop an approach to use knowledge about the semantics via data augmentations. These data augmentations cor- rupt semantic information to produce models that identify and adjust for where nuisances drive predictions. We study semantic corruptions in powering different spurious-correlation- avoiding methods on multiple out-of-distribution (ood) tasks like classifying waterbirds, natural language inference (nli), and detecting cardiomegaly in chest X-rays.

PDF Details

TMLR Journal 2024 Journal Article

Weighted Risk Invariance: Domain Generalization under Invariant Feature Shift

Gina Wong
Joshua Gleason
Rama Chellappa
Yoav Wald
Anqi Liu

Learning models whose predictions are invariant under multiple environments is a promising approach for out-of-distribution generalization. Such models are trained to extract features $X_{\text{inv}}$ where the conditional distribution $Y \mid X_{\text{inv}}$ of the label given the extracted features does not change across environments. Invariant models are also supposed to generalize to shifts in the marginal distribution $p(X_{\text{inv}})$ of the extracted features $X_{\text{inv}}$, a type of shift we call an invariant covariate shift. However, we show that proposed methods for learning invariant models underperform under invariant covariate shift, either failing to learn invariant models---even for data generated from simple and well-studied linear-Gaussian models---or having poor finite-sample performance. To alleviate these problems, we propose weighted risk invariance (WRI). Our framework is based on imposing invariance of the loss across environments subject to appropriate reweightings of the training examples. We show that WRI provably learns invariant models, i.e. discards spurious correlations, in linear-Gaussian settings. We propose a practical algorithm to implement WRI by learning the density $p(X_{\text{inv}})$ and the model parameters simultaneously, and we demonstrate empirically that WRI outperforms previous invariant learning methods under invariant covariate shift.

PDF Details

UAI Conference 2023 Conference Paper

Birds of an odd feather: guaranteed out-of-distribution (OOD) novel category detection

Yoav Wald
Suchi Saria

In this work, we solve the problem of novel category detection under distribution shift. This problem is critical to ensuring the safety and efficacy of machine learning models, particularly in domains such as healthcare where timely detection of novel subgroups of patients is crucial. To address this problem, we propose a method based on constrained learning. Our approach is guaranteed to detect a novel category under a relatively weak assumption, namely that rare events in past data have bounded frequency under the shifted distribution. Prior works on the problem do not provide such guarantees, as they either attend to very specific types of distribution shift or make stringent assumptions that limit their guarantees. We demonstrate favorable performance of our method on challenging novel category detection problems over real world datasets.

Details

NeurIPS Conference 2023 Conference Paper

Data Augmentations for Improved (Large) Language Model Generalization

Amir Feder
Yoav Wald
Claudia Shi
Suchi Saria
David Blei

The reliance of text classifiers on spurious correlations can lead to poor generalization at deployment, raising concerns about their use in safety-critical domains such as healthcare. In this work, we propose to use counterfactual data augmentation, guided by knowledge of the causal structure of the data, to simulate interventions on spurious features and to learn more robust text classifiers. We show that this strategy is appropriate in prediction problems where the label is spuriously correlated with an attribute. Under the assumptions of such problems, we discuss the favorable sample complexity of counterfactual data augmentation, compared to importance re-weighting. Pragmatically, we match examples using auxiliary data, based on diff-in-diff methodology, and use a large language model (LLM) to represent a conditional probability of text. Through extensive experimentation on learning caregiver-invariant predictors of clinical diagnoses from medical narratives and on semi-synthetic data, we demonstrate that our method for simulating interventions improves out-of-distribution (OOD) accuracy compared to baseline invariant learning algorithms.

PDF Details

NeurIPS Conference 2023 Conference Paper

Don’t blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy

Aahlad Puli
Lily Zhang
Yoav Wald
Rajesh Ranganath

Common explanations for shortcut learning assume that the shortcut improves prediction only under the training distribution. Thus, models trained in the typical way by minimizing log-loss using gradient descent, which we call default-ERM, should utilize the shortcut. However, even when the stable feature determines the label in the training distribution and the shortcut does not provide any additional information, like in perception tasks, default-ERM exhibits shortcut learning. Why are such solutions preferred when the loss can be driven to zero when using the stable feature alone? By studying a linear perception task, we show that default-ERM’s preference for maximizing the margin, even without overparameterization, leads to models that depend more on the shortcut than the stable feature. This insight suggests that default-ERM’s implicit inductive bias towards max-margin may be unsuitable for perception tasks. Instead, we consider inductive biases toward uniform margins. We show that uniform margins guarantee sole dependence on the perfect stable feature in the linear perception task and suggest alternative loss functions, termed margin control (MARG-CTRL), that encourage uniform-margin solutions. MARG-CTRL techniques mitigate shortcut learning on a variety of vision and language tasks, showing that changing inductive biases can remove the need for complicated shortcut-mitigating methods in perception tasks.

PDF Details

ICLR Conference 2023 Conference Paper

Malign Overfitting: Interpolation and Invariance are Fundamentally at Odds

Yoav Wald
Gal Yona
Uri Shalit
Yair Carmon

Learned classifiers should often possess certain invariance properties meant to encourage fairness, robustness, or out-of-distribution generalization. However, multiple recent works empirically demonstrate that common invariance-inducing regularizers are ineffective in the over-parameterized regime, in which classifiers perfectly fit (i.e. interpolate) the training data. This suggests that the phenomenon of ``benign overfitting," in which models generalize well despite interpolating, might not favorably extend to settings in which robustness or fairness are desirable. In this work, we provide a theoretical justification for these observations. We prove that---even in the simplest of settings---any interpolating learning rule (with an arbitrarily small margin) will not satisfy these invariance properties. We then propose and analyze an algorithm that---in the same setting---successfully learns a non-interpolating classifier that is provably invariant. We validate our theoretical observations on simulated data and the Waterbirds dataset.

Details

NeurIPS Conference 2022 Conference Paper

In the Eye of the Beholder: Robust Prediction with Causal User Modeling

Amir Feder
Guy Horowitz
Yoav Wald
Roi Reichart
Nir Rosenfeld

Accurately predicting the relevance of items to users is crucial to the success of many social platforms. Conventional approaches train models on logged historical data; but recommendation systems, media services, and online marketplaces all exhibit a constant influx of new content---making relevancy a moving target, to which standard predictive models are not robust. In this paper, we propose a learning framework for relevance prediction that is robust to changes in the data distribution. Our key observation is that robustness can be obtained by accounting for \emph{how users causally perceive the environment}. We model users as boundedly-rational decision makers whose causal beliefs are encoded by a causal graph, and show how minimal information regarding the graph can be used to contend with distributional changes. Experiments in multiple settings demonstrate the effectiveness of our approach.

PDF Details

NeurIPS Conference 2021 Conference Paper

On Calibration and Out-of-Domain Generalization

Yoav Wald
Amir Feder
Daniel Greenfeld
Uri Shalit

Out-of-domain (OOD) generalization is a significant challenge for machine learning models. Many techniques have been proposed to overcome this challenge, often focused on learning models with certain invariance properties. In this work, we draw a link between OOD performance and model calibration, arguing that calibration across multiple domains can be viewed as a special case of an invariant representation leading to better OOD generalization. Specifically, we show that under certain conditions, models which achieve \emph{multi-domain calibration} are provably free of spurious correlations. This leads us to propose multi-domain calibration as a measurable and trainable surrogate for the OOD performance of a classifier. We therefore introduce methods that are easy to apply and allow practitioners to improve multi-domain calibration by training or modifying an existing model, leading to better performance on unseen domains. Using four datasets from the recently proposed WILDS OOD benchmark, as well as the Colored MNIST, we demonstrate that training or tuning models so they are calibrated across multiple domains leads to significantly improved performance on unseen test domains. We believe this intriguing connection between calibration and OOD generalization is promising from both a practical and theoretical point of view.

PDF Details

NeurIPS Conference 2019 Conference Paper

Globally Optimal Learning for Structured Elliptical Losses

Yoav Wald
Nofar Noy
Gal Elidan
Ami Wiesel

Heavy tailed and contaminated data are common in various applications of machine learning. A standard technique to handle regression tasks that involve such data, is to use robust losses, e. g. , the popular Huber’s loss. In structured problems, however, where there are multiple labels and structural constraints on the labels are imposed (or learned), robust optimization is challenging, and more often than not the loss used is simply the negative log-likelihood of a Gaussian Markov random field. Heavy tailed and contaminated data are common in various applications of machine learning. A standard technique to handle regression tasks that involve such data, is to use robust losses, e. g. , the popular Huber’s loss. In structured problems, however, where there are multiple labels and structural constraints on the labels are imposed (or learned), robust optimization is challenging, and more often than not the loss used is simply the negative log-likelihood of a Gaussian Markov random field. In this work, we analyze robust alternatives. Theoretical understanding of such problems is quite limited, with guarantees on optimization given only for special cases and non-structured settings. The core of the difficulty is the non-convexity of the objective function, implying that standard optimization algorithms may converge to sub-optimal critical points. Our analysis focuses on loss functions that arise from elliptical distributions, which appealingly include most loss functions proposed in the literature as special cases. We show that, even though these problems are non-convex, they can be optimized efficiently. Concretely, we prove that at the limit of infinite training data, due to algebraic properties of the problem, all stationary points are globally optimal. Finally, we demonstrate the empirical appeal of using these losses for regression on synthetic and real-life data.

PDF Details

NeurIPS Conference 2017 Conference Paper

Robust Conditional Probabilities

Yoav Wald
Amir Globerson

Conditional probabilities are a core concept in machine learning. For example, optimal prediction of a label $Y$ given an input $X$ corresponds to maximizing the conditional probability of $Y$ given $X$. A common approach to inference tasks is learning a model of conditional probabilities. However, these models are often based on strong assumptions (e. g. , log-linear models), and hence their estimate of conditional probabilities is not robust and is highly dependent on the validity of their assumptions. Here we propose a framework for reasoning about conditional probabilities without assuming anything about the underlying distributions, except knowledge of their second order marginals, which can be estimated from data. We show how this setting leads to guaranteed bounds on conditional probabilities, which can be calculated efficiently in a variety of settings, including structured-prediction. Finally, we apply them to semi-supervised deep learning, obtaining results competitive with variational autoencoders.

PDF Details

UAI Conference 2014 Conference Paper

Tightness Results for Local Consistency Relaxations in Continuous MRFs

Yoav Wald
Amir Globerson

Finding the MAP assignment in graphical models is a challenging task that generally requires approximations. One popular approximation approach is to use linear programming relaxations that enforce local consistency. While these are commonly used for discrete variable models, they are much less understood for models with continuous variables. Here we define local consistency relaxations of MAP for continuous pairwise Markov Random Fields (MRFs), and analyze their properties. We begin by providing a characterization of models for which this relaxation is tight. These turn out to be models that can be reparameterized as a sum of local convex functions. We also provide a simple formulation of this relaxation for Gaussian MRFs. Next, we show how the above insights can be used to obtain optimality certificates for loopy belief propagation (LBP) in such models. Specifically, we show that the messages of LBP can be used to calculate upper and lower bounds on the MAP value, and that these bounds coincide at convergence, yielding a natural stopping criterion which was not previously available. Finally, our results illustrate a close connection between local consistency relaxations of MAP and LBP. They demonstrate that in the continuous case, whenever LBP is provably optimal so is the local consistency relaxation.

Details