Elena Zheleva

Ragib Ahsan, David Arbour, Elena Zheleva

In real-world phenomena which involve mutual influence or causal effects between interconnected units, equilibrium states are typically represented with cycles in graphical models. An expressive class of graphical models, relational causal models, can represent and reason about complex dynamic systems exhibiting such cycles or feedback loops. Existing cyclic causal discovery algorithms for learning causal models from observational data assume that the data instances are independent and identically distributed which makes them unsuitable for relational causal models. At the same time, causal discovery algorithms for relational causal models assume acyclicity. In this work, we examine the necessary and sufficient conditions under which a constraint-based relational causal discovery algorithm is sound and complete for cyclic relational causal models. We introduce relational acyclification, an operation specifically designed for relational models that enables reasoning about the identifiability of cyclic relational causal models. We show that under the assumptions of relational acyclification and $σ$-faithfulness, the relational causal discovery algorithm RCD (Maier et al. 2013) is sound and complete for cyclic models. We present experimental results to support our claim.

Christopher Tran, Elena Zheleva

Estimating how a treatment affects units individually, known as heterogeneous treatment effect (HTE) estimation, is an essential part of decision-making and policy implementation. The accumulation of large amounts of data in many domains, such as healthcare and e-commerce, has led to increased interest in developing data-driven algorithms for estimating heterogeneous effects from observational and experimental data. However, these methods often make strong assumptions about the observed features and ignore the underlying causal model structure, which can lead to biased HTE estimation. At the same time, accounting for the causal structure of real-world data is rarely trivial since the causal mechanisms that gave rise to the data are typically unknown. To address this problem, we develop a feature selection method that considers each feature's value for HTE estimation and learns the relevant parts of the causal structure from data. We provide strong empirical evidence that our method improves existing data-driven HTE estimation methods under arbitrary underlying causal structures. Our results on synthetic, semi-synthetic, and real-world datasets show that our feature selection algorithm leads to lower HTE estimation error.

Zahra Fatemi, Minh Huynh, Elena Zheleva et al.

Forecasting multivariate time series data, which involves predicting future values of variables over time using historical data, has significant practical applications. Although deep learning-based models have shown promise in this field, they often fail to capture the causal relationship between dependent variables, leading to less accurate forecasts. Additionally, these models cannot handle the cold-start problem in time series data, where certain variables lack historical data, posing challenges in identifying dependencies among variables. To address these limitations, we introduce the Cold Causal Demand Forecasting (CDF-cold) framework that integrates causal inference with deep learning-based models to enhance the forecasting accuracy of multivariate time series data affected by the cold-start problem. To validate the effectiveness of the proposed approach, we collect 15 multivariate time-series datasets containing the network traffic of different Google data centers. Our experiments demonstrate that the CDF-cold framework outperforms state-of-the-art forecasting models in predicting future values of multivariate time series data.

Zahra Fatemi, Elena Zheleva

Contagion effect refers to the causal effect of peers' behavior on the outcome of an individual in social networks. Contagion can be confounded due to latent homophily which makes contagion effect estimation very hard: nodes in a homophilic network tend to have ties to peers with similar attributes and can behave similarly without influencing one another. One way to account for latent homophily is by considering proxies for the unobserved confounders. However, as we demonstrate in this paper, existing proxy-based methods for contagion effect estimation have a very high variance when the proxies are high-dimensional. To address this issue, we introduce a novel framework, Proximal Embeddings (ProEmb), that integrates variational autoencoders with adversarial networks to create low-dimensional representations of high-dimensional proxies and help with identifying contagion effects. While VAEs have been used previously for representation learning in causal inference, a novel aspect of our approach is the additional component of adversarial networks to balance the representations of different treatment groups, which is essential in causal inference from observational data where these groups typically come from different distributions. We empirically show that our method significantly increases the accuracy and reduces the variance of contagion effect estimation in observational network data compared to state-of-the-art methods.

Christopher Tran, Keith Burghardt, Kristina Lerman et al.

Estimating how a treatment affects different individuals, known as heterogeneous treatment effect estimation, is an important problem in empirical sciences. In the last few years, there has been a considerable interest in adapting machine learning algorithms to the problem of estimating heterogeneous effects from observational and experimental data. However, these algorithms often make strong assumptions about the observed features in the data and ignore the structure of the underlying causal model, which can lead to biased estimation. At the same time, the underlying causal mechanism is rarely known in real-world datasets, making it hard to take it into consideration. In this work, we provide a survey of state-of-the-art data-driven methods for heterogeneous treatment effect estimation using machine learning, broadly categorizing them as methods that focus on counterfactual prediction and methods that directly estimate the causal effect. We also provide an overview of a third category of methods which rely on structural causal models and learn the model structure from data. Our empirical evaluation under various underlying structural model mechanisms shows the advantages and deficiencies of existing estimators and of the metrics for measuring their performance.

Ragib Ahsan, Zahra Fatemi, David Arbour et al.

Independence testing plays a central role in statistical and causal inference from observational data. Standard independence tests assume that the data samples are independent and identically distributed (i.i.d.) but that assumption is violated in many real-world datasets and applications centered on relational systems. This work examines the problem of estimating independence in data drawn from relational systems by defining sufficient representations for the sets of observations influencing individual instances. Specifically, we define marginal and conditional independence tests for relational data by considering the kernel mean embedding as a flexible aggregation function for relational variables. We propose a consistent, non-parametric, scalable kernel test to operationalize the relational independence test for non-i.i.d. observational data under a set of structural assumptions. We empirically evaluate our proposed method on a variety of synthetic and semi-synthetic networks and demonstrate its effectiveness compared to state-of-the-art kernel-based independence tests.

Rafat Ashraf Joy, Elena Zheleva

Learning causal relations from observational data is challenging because the graph search space grows super-exponentially with the number of variables. Ordering-based methods reduce this space by first identifying the topological ordering, whereas continuous optimization methods explore most likely regions of the space by casting DAG learning as a differentiable objective with an acyclicity constraint. Despite their conceptual appeal, both paradigms face significant scalability limitations in high-dimensional settings, restricting their practical applicability. In this work, we introduce a new formulation for linear causal discovery that tightly integrates these two paradigms to achieve substantial gains in scalability without sacrificing accuracy. Our approach, TriOpt, decomposes the problem into two efficient stages. First, it recovers the topological ordering by exploiting the Sherman-Morrison rank-1 downdate together with the additive structure of linear kernels, enabling fast and scalable ordering estimation. Second, given this ordering, we reformulate structure learning as a convex continuous optimization problem that entirely avoids the need for enforcing costly acyclicity constraints. We theoretically show that, under the true ordering, TriOpt exactly recovers the underlying linear DAG. Empirically, across synthetic, semi-synthetic, and real-world datasets, TriOpt achieves orders-of-magnitude speedups over state-of-the-art linear causal discovery methods in high-dimensional regimes, while maintaining comparable or superior accuracy.

Md Aminul Islam, Ahmed Sayeed Faruk, Sourav Medya et al.

Collaborative filtering (CF) models based on graph neural networks (GNNs) achieve strong performance in recommender systems by propagating user-item signals over interaction graphs. However, they are highly susceptible to popularity bias, since skewed interaction distributions and repeated message passing across high-order neighborhoods amplify the influence of popular items while suppressing long-tail ones. Existing debiasing approaches, including re-weighting objectives, regularization, causal methods, and post-processing, are less effective in GNN-based settings because they do not directly counteract bias propagated through the aggregation process, and recent in-aggregation weighting methods often rely on static heuristics or unstable embedding estimates. We propose Debiasing Popularity Amplification in Aggregation (DPAA), a popularity debiasing framework for GNN-based CF that integrates adaptive, embedding-aware interaction weighting and layer-wise weighting directly into message passing. DPAA assigns interaction-level weights from a representation-aware popularity signal, stabilized by a smooth transition from pre-trained to evolving model embeddings during training. It further introduces a layer-wise weighting that amplifies higher-order neighborhoods, surfacing long-range interactions with diverse and underexposed items. Experiments on real-world and semi-synthetic datasets show that DPAA outperforms state-of-the-art popularity-bias correction methods for GNN-based CF.

Zohreh Ovaisi, Shelby Heinecke, Jia Li et al.

Robust machine learning is an increasingly important topic that focuses on developing models resilient to various forms of imperfect data. Due to the pervasiveness of recommender systems in online technologies, researchers have carried out several robustness studies focusing on data sparsity and profile injection attacks. Instead, we propose a more holistic view of robustness for recommender systems that encompasses multiple dimensions - robustness with respect to sub-populations, transformations, distributional disparity, attack, and data sparsity. While there are several libraries that allow users to compare different recommender system models, there is no software library for comprehensive robustness evaluation of recommender system models under different scenarios. As our main contribution, we present a robustness evaluation toolkit, Robustness Gym for RecSys (RGRecSys -- https://www.github.com/salesforce/RGRecSys), that allows us to quickly and uniformly evaluate the robustness of recommender system models.

Ahmed Sayeed Faruk, Elena Zheleva

Recommender systems relying on contextual multi-armed bandits continuously improve relevant item recommendations by taking into account the contextual information. The objective of bandit algorithms is to learn the best arm (e.g., best item to recommend) for each user and thus maximize the cumulative rewards from user engagement with the recommendations. The context that these algorithms typically consider are the user and item attributes. However, in the context of social networks where $\textit{the action of one user can influence the actions and rewards of other users,}$ neighbors' actions are also a very important context, as they can have not only predictive power but also can impact future rewards through spillover. Moreover, influence susceptibility can vary for different people based on their preferences and the closeness of ties to other users which leads to heterogeneity in the spillover effects. Here, we present a framework that allows contextual multi-armed bandits to account for such heterogeneous spillovers when choosing the best arm for each user. Our experiments on several semi-synthetic and real-world datasets show that our framework leads to significantly higher rewards than existing state-of-the-art solutions that ignore the network information and potential spillover.

Md Aminul Islam, Elena Zheleva, Ren Wang

User historical interaction data is the primary signal for learning user preferences in collaborative filtering (CF). However, the training data often exhibits a long-tailed distribution, where only a few items have the majority of interactions. CF models trained directly on such imbalanced data are prone to learning popularity bias, which reduces personalization and leads to suboptimal recommendation quality. Graph Neural Networks (GNNs), while effective for CF due to their message passing mechanism, can further propagate and amplify popularity bias through their aggregation process. Existing approaches typically address popularity bias by modifying training objectives but fail to directly counteract the bias propagated during GNN's neighborhood aggregation. Applying weights to interactions during aggregation can help alleviate this problem, yet it risks distorting model learning due to unstable node representations in the early stages of training. In this paper, we propose a Post-hoc Popularity Debiasing (PPD) method that corrects for popularity bias in GNN-based CF and operates directly on pre-trained embeddings without requiring retraining. By estimating interaction-level popularity and removing popularity components from node representations via a popularity direction vector, PPD reduces bias while preserving user preferences. Experimental results show that our method outperforms state-of-the-art approaches for popularity bias correction in GNN-based CF.

Rochana Chaturvedi, Sugat Chaturvedi, Elena Zheleva

While exposure to diverse viewpoints may reduce polarization, it can also have a backfire effect and exacerbate polarization when the discussion is adversarial. Here, we examine the question whether intergroup interactions around important events affect polarization between majority and minority groups in social networks. We compile data on the religious identity of nearly 700,000 Indian Twitter users engaging in COVID-19-related discourse during 2020. We introduce a new measure for an individual's group conformity based on contextualized embeddings of tweet text, which helps us assess polarization between religious groups. We then use a meta-learning framework to examine heterogeneous treatment effects of intergroup interactions on an individual's group conformity in the light of communal, political, and socio-economic events. We find that for political and social events, intergroup interactions reduce polarization. This decline is weaker for individuals at the extreme who already exhibit high conformity to their group. In contrast, during communal events, intergroup interactions can increase group conformity. Finally, we decompose the differential effects across religious groups in terms of emotions and topics of discussion. The results show that the dynamics of religious polarization are sensitive to the context and have important implications for understanding the role of intergroup interactions.

Md Aminul Islam, Kathryn Vasilaky, Elena Zheleva

Implicit feedback data, such as user clicks, is commonly used in learning-to-rank (LTR) systems because it is easy to collect and it often reflects user preferences. However, this data is prone to various biases, and training an LTR system directly on biased data can result in suboptimal ranking performance. One of the most prominent and well-studied biases in implicit feedback data is position bias, which occurs because users are more likely to interact with higher-ranked documents regardless of their true relevance. In this paper, we propose a novel control function-based method that accounts for position bias in a two-stage process. The first stage uses exogenous variation from the residuals of the ranking process to correct for position bias in the second stage click equation. Unlike previous position bias correction methods, our method does not require knowledge of the click or propensity model and allows for nonlinearity in the underlying ranking model. Moreover, our method is general and allows for debiasing any state-of-the-art ranking algorithm by plugging it into the second stage. We also introduce a technique to debias validation clicks for hyperparameter tuning to select the optimal model in the absence of unbiased validation data. Experimental results demonstrate that our method outperforms state-of-the-art approaches in correcting for position bias.

Shishir Adhikari, Sourav Medya, Elena Zheleva

In causal inference, interference refers to the phenomenon in which the actions of peers in a network can influence an individual's outcome. Peer effect refers to the difference in counterfactual outcomes of an individual for different levels of peer exposure, the extent to which an individual is exposed to the treatments, actions, or behaviors of peers. Estimating peer effects requires deciding how to represent peer exposure. Typically, researchers define an exposure mapping function that aggregates peer treatments and outputs peer exposure. Most existing approaches for defining exposure mapping functions assume peer exposure based on the number or fraction of treated peers. Recent studies have investigated more complex functions of peer exposure which capture that different peers can exert different degrees of influence. However, none of these works have explicitly considered the problem of automatically learning the exposure mapping function. In this work, we focus on learning this function for the purpose of estimating heterogeneous peer effects, where heterogeneity refers to the variation in counterfactual outcomes for the same peer exposure but different individual's contexts. We develop EgoNetGNN, a graph neural network (GNN)-based method, to automatically learn the appropriate exposure mapping function allowing for complex peer influence mechanisms that, in addition to peer treatments, can involve the local neighborhood structure and edge attributes. We show that GNN models that use peer exposure based on the number or fraction of treated peers or learn peer exposure naively face difficulty accounting for such influence mechanisms. Our comprehensive evaluation on synthetic and semi-synthetic network data shows that our method is more robust to different unknown underlying influence mechanisms when estimating heterogeneous peer effects when compared to state-of-the-art baselines.

Ahmed Sayeed Faruk, Mohammad Shahverdikondori, Elena Zheleva

In networked environments, users frequently share recommendations about content, products, services, and courses of action with others. The extent to which such recommendations are successful and adopted is highly contextual, dependent on the characteristics of the sender, recipient, their relationship, the recommended item, and the medium, which makes peer influence probabilities highly heterogeneous. Accurate estimation of these probabilities is key to understanding information diffusion processes and to improving the effectiveness of viral marketing strategies. However, learning these probabilities from data is challenging; static data may capture correlations between peer recommendations and peer actions but fails to reveal influence relationships. Online learning algorithms can learn these probabilities from interventions but either waste resources by learning from random exploration or optimize for rewards, thus favoring exploration of the space with higher influence probabilities. In this work, we study learning peer influence probabilities under a contextual linear bandit framework. We show that a fundamental trade-off can arise between regret minimization and estimation error, characterize all achievable rate pairs, and propose an uncertainty-guided exploration algorithm that, by tuning a parameter, attains any pair within this trade-off. Our experiments on semi-synthetic network datasets show the advantages of our method over static methods and contextual bandits that ignore this trade-off.

Jifan Zhang, Michelle M. Li, Elena Zheleva

Causal disentanglement from soft interventions is identifiable under the assumptions of linear interventional faithfulness and availability of both observational and interventional data. Previous research has looked into this problem from the perspective of i.i.d. data. Here, we develop a framework, GraCE-VAE, for non-i.i.d. settings, in which structured context in the form of network data is available. GraCE-VAE integrates discrepancy-based variational autoencoders with graph neural networks to jointly recover the true latent causal graph and intervention effects. We show that the theoretical results of identifiability from i.i.d. data hold in our setup. We also empirically evaluate GraCE-VAE against state-of-the-art baselines on three genetic perturbation datasets to demonstrate the impact of leveraging structured context for causal disentanglement.

Matteo Negro, Andrea Piras, Ragib Ahsan et al.

Estimating causal effects from real-world relational data can be challenging when the underlying causal model and potential confounders are unknown. While several causal discovery algorithms exist for learning causal models with latent confounders from data, they assume that the data is independent and identically distributed (i.i.d.) and are not well-suited for learning from relational data. Similarly, existing relational causal discovery algorithms assume causal sufficiency, which is unrealistic for many real-world datasets. To address this gap, we propose RelFCI, a sound and complete causal discovery algorithm for relational data with latent confounders. Our work builds upon the Fast Causal Inference (FCI) and Relational Causal Discovery (RCD) algorithms and it defines new graphical models, necessary to support causal discovery in relational domains. We also establish soundness and completeness guarantees for relational d-separation with latent confounders. We present experimental results demonstrating the effectiveness of RelFCI in identifying the correct causal structure in relational causal models with latent confounders.

Ahmed Sayeed Faruk, Jason Sulskis, Elena Zheleva

The gold standard for estimating causal effects is randomized controlled trial (RCT) or A/B testing where a random group of individuals from a population of interest are given treatment and the outcome is compared to a random group of individuals from the same population. However, A/B testing is challenging in the presence of interference, commonly occurring in social networks, where individuals can impact each others outcome. Moreover, A/B testing can incur a high performance loss when one of the treatment arms has a poor performance and the test continues to treat individuals with it. Therefore, it is important to design a strategy that can adapt over time and efficiently learn the total treatment effect in the network. We introduce two cluster-based multi-armed bandit (MAB) algorithms to gradually estimate the total treatment effect in a network while maximizing the expected reward by making a tradeoff between exploration and exploitation. We compare the performance of our MAB algorithms with a vanilla MAB algorithm that ignores clusters and the corresponding RCT methods on semi-synthetic data with simulated interference. The vanilla MAB algorithm shows higher reward-action ratio at the cost of higher treatment effect error due to undesired spillover. The cluster-based MAB algorithms show higher reward-action ratio compared to their corresponding RCT methods without sacrificing much accuracy in treatment effect estimation.

Shishir Adhikari, Guido Muscioni, Mark Shapiro et al.

Understanding factors triggering or preventing undesirable health outcomes across patient subpopulations is essential for designing targeted interventions. While randomized controlled trials and expert-led patient interviews are standard methods for identifying these factors, they can be time-consuming and infeasible. Causal discovery offers an alternative to conventional approaches by generating cause-and-effect hypotheses from observational data. However, it often relies on strong or untestable assumptions, which can limit its practical application. This work aims to make causal discovery more practical by considering multiple assumptions and identifying heterogeneous effects. We formulate the problem of discovering causes and effect modifiers of an outcome, where effect modifiers are contexts (e.g., age groups) with heterogeneous causal effects. Then, we present a novel, end-to-end framework that incorporates an ensemble of causal discovery algorithms and estimation of heterogeneous effects to discover causes and effect modifiers that trigger or inhibit the outcome. We demonstrate that the ensemble approach improves robustness by enhancing recall of causal factors while maintaining precision. Our study examines the causes of repeat emergency room visits for diabetic patients and hospital readmissions for ICU patients. Our framework generates causal hypotheses consistent with existing literature and can help practitioners identify potential interventions and patient subpopulations to focus on.

Zahra Fatemi, Jean Pouget-Abadie, Elena Zheleva

The presence of interference, where the outcome of an individual may depend on the treatment assignment and behavior of neighboring nodes, can lead to biased causal effect estimation. Current approaches to network experiment design focus on limiting interference through cluster-based randomization, in which clusters are identified using graph clustering, and cluster randomization dictates the node assignment to treatment and control. However, cluster-based randomization approaches perform poorly when interference propagates in cascades, whereby the response of individuals to treatment propagates to their multi-hop neighbors. When we have knowledge of the cascade seed nodes, we can leverage this interference structure to mitigate the resulting causal effect estimation bias. With this goal, we propose a cascade-based network experiment design that initiates treatment assignment from the cascade seed node and propagates the assignment to their multi-hop neighbors to limit interference during cascade growth and thereby reduce the overall causal effect estimation error. Our extensive experiments on real-world and synthetic datasets demonstrate that our proposed framework outperforms the existing state-of-the-art approaches in estimating causal effects in network data.

Shishir Adhikari, Elena Zheleva

Causal inference in networks should account for interference, which occurs when a unit's outcome is influenced by treatments or outcomes of peers. Heterogeneous peer influence (HPI) occurs when a unit's outcome is influenced differently by different peers based on their attributes and relationships, or when each unit has a different susceptibility to peer influence. Existing solutions to estimating direct causal effects under interference consider either homogeneous influence from peers or specific heterogeneous influence mechanisms (e.g., based on local neighborhood structure). This paper presents a methodology for estimating individual direct causal effects in the presence of HPI where the mechanism of influence is not known a priori. We propose a structural causal model for networks that can capture different possible assumptions about network structure, interference conditions, and causal dependence and enables reasoning about identifiability in the presence of HPI. We find potential heterogeneous contexts using the causal model and propose a novel graph neural network-based estimator to estimate individual direct causal effects. We show that state-of-the-art methods for individual direct effect estimation produce biased results in the presence of HPI, and that our proposed estimator is robust.

Ragib Ahsan, David Arbour, Elena Zheleva

Causal reasoning in relational domains is fundamental to studying real-world social phenomena in which individual units can influence each other's traits and behavior. Dynamics between interconnected units can be represented as an instantiation of a relational causal model; however, causal reasoning over such instantiation requires additional templating assumptions that capture feedback loops of influence. Previous research has developed lifted representations to address the relational nature of such dynamics but has strictly required that the representation has no cycles. To facilitate cycles in relational representation and learning, we introduce relational $σ$-separation, a new criterion for understanding relational systems with feedback loops. We also introduce a new lifted representation, $σ$-abstract ground graph which helps with abstracting statistical independence relations in all possible instantiations of the cyclic relational model. We show the necessary and sufficient conditions for the completeness of $σ$-AGG and that relational $σ$-separation is sound and complete in the presence of one or more cycles with arbitrary length. To the best of our knowledge, this is the first work on representation of and reasoning with cyclic relational causal models.

Christopher Tran, Elena Zheleva

The Linear Threshold Model is a widely used model that describes how information diffuses through a social network. According to this model, an individual adopts an idea or product after the proportion of their neighbors who have adopted it reaches a certain threshold. Typical applications of the Linear Threshold Model assume that thresholds are either the same for all network nodes or randomly distributed, even though some people may be more susceptible to peer pressure than others. To address individual-level differences, we propose causal inference methods for estimating individual thresholds that can more accurately predict whether and when individuals will be affected by their peers. We introduce the concept of heterogeneous peer effects and develop a Structural Causal Model which corresponds to the Linear Threshold Model and supports heterogeneous peer effect identification and estimation. We develop two algorithms for individual threshold estimation, one based on causal trees and one based on causal meta-learners. Our experimental results on synthetic and real-world datasets show that our proposed models can better predict individual-level thresholds in the Linear Threshold Model and thus more precisely predict which nodes will get activated over time.

Yuzi He, Christopher Tran, Julie Jiang et al.

The popularity of online gaming has grown dramatically, driven in part by streaming and the billion-dollar e-sports industry. Online games regularly update their software to fix bugs, add functionality that improve the game's look and feel, and change the game mechanics to keep the games fun and challenging. An open question, however, is the impact of these changes on player performance and game balance, as well as how players adapt to these sudden changes. To address these questions, we use causal inference to measure the impact of software patches to League of Legends, a popular team-based multiplayer online game. We show that game patches have substantially different impacts on players depending on their skill level and whether they take breaks between games. We find that the gap between good and bad players increases after a patch, despite efforts to make gameplay more equal. Moreover, longer between-game breaks tend to improve player performance after patches. Overall, our results highlight the utility of causal inference, and specifically heterogeneous treatment effect estimation, as a tool to quantify the complex mechanisms of game balance and its interplay with players' performance.

Shishir Adhikari, Akshay Uppal, Robin Mermelstein et al.

Cannabis legalization has been welcomed by many U.S. states but its role in escalation from tobacco e-cigarette use to cannabis vaping is unclear. Meanwhile, cannabis vaping has been associated with new lung diseases and rising adolescent use. To understand the impact of cannabis legalization on escalation, we design an observational study to estimate the causal effect of recreational cannabis legalization on the development of pro-cannabis attitude for e-cigarette users. We collect and analyze Twitter data which contains opinions about cannabis and JUUL, a very popular e-cigarette brand. We use weakly supervised learning for personal tweet filtering and classification for stance detection. We discover that recreational cannabis legalization policy has an effect on increased development of pro-cannabis attitudes for users already in favor of e-cigarettes.

Zahra Fatemi, Elena Zheleva

Current approaches to A/B testing in networks focus on limiting interference, the concern that treatment effects can "spill over" from treatment nodes to control nodes and lead to biased causal effect estimation. Prominent methods for network experiment design rely on two-stage randomization, in which sparsely-connected clusters are identified and cluster randomization dictates the node assignment to treatment and control. Here, we show that cluster randomization does not ensure sufficient node randomization and it can lead to selection bias in which treatment and control nodes represent different populations of users. To address this problem, we propose a principled framework for network experiment design which jointly minimizes interference and selection bias. We introduce the concepts of edge spillover probability and cluster matching and demonstrate their importance for designing network A/B testing. Our experiments on a number of real-world datasets show that our proposed framework leads to significantly lower error in causal effect estimation than existing solutions.

Chainarong Amornbunchornvej, Elena Zheleva, Tanya Berger-Wolf

Granger causality is a fundamental technique for causal inference in time series data, commonly used in the social and biological sciences. Typical operationalizations of Granger causality make a strong assumption that every time point of the effect time series is influenced by a combination of other time series with a fixed time delay. The assumption of fixed time delay also exists in Transfer Entropy, which is considered to be a non-linear version of Granger causality. However, the assumption of the fixed time delay does not hold in many applications, such as collective behavior, financial markets, and many natural phenomena. To address this issue, we develop Variable-lag Granger causality and Variable-lag Transfer Entropy, generalizations of both Granger causality and Transfer Entropy that relax the assumption of the fixed time delay and allow causes to influence effects with arbitrary time delays. In addition, we propose methods for inferring both variable-lag Granger causality and Transfer Entropy relations. In our approaches, we utilize an optimal warping path of Dynamic Time Warping (DTW) to infer variable-lag causal relations. We demonstrate our approaches on an application for studying coordinated collective behavior and other real-world casual-inference datasets and show that our proposed approaches perform better than several existing methods in both simulated and real-world datasets. Our approaches can be applied in any domain of time series analysis. The software of this work is available in the R-CRAN package: VLTimeCausality.

Zohreh Ovaisi, Ragib Ahsan, Yifan Zhang et al.

Click data collected by modern recommendation systems are an important source of observational data that can be utilized to train learning-to-rank (LTR) systems. However, these data suffer from a number of biases that can result in poor performance for LTR systems. Recent methods for bias correction in such systems mostly focus on position bias, the fact that higher ranked results (e.g., top search engine results) are more likely to be clicked even if they are not the most relevant results given a user's query. Less attention has been paid to correcting for selection bias, which occurs because clicked documents are reflective of what documents have been shown to the user in the first place. Here, we propose new counterfactual approaches which adapt Heckman's two-stage method and accounts for selection and position bias in LTR systems. Our empirical evaluation shows that our proposed methods are much more robust to noise and have better accuracy compared to existing unbiased LTR algorithms, especially when there is moderate to no position bias.

Chainarong Amornbunchornvej, Elena Zheleva, Tanya Y. Berger-Wolf

Granger causality is a fundamental technique for causal inference in time series data, commonly used in the social and biological sciences. Typical operationalizations of Granger causality make a strong assumption that every time point of the effect time series is influenced by a combination of other time series with a fixed time delay. However, the assumption of the fixed time delay does not hold in many applications, such as collective behavior, financial markets, and many natural phenomena. To address this issue, we develop variable-lag Granger causality, a generalization of Granger causality that relaxes the assumption of the fixed time delay and allows causes to influence effects with arbitrary time delays. In addition, we propose a method for inferring variable-lag Granger causality relations. We demonstrate our approach on an application for studying coordinated collective behavior and show that it performs better than several existing methods in both simulated and real-world datasets. Our approach can be applied in any domain of time series analysis.

Christopher Tran, Elena Zheleva

The causal effect of a treatment can vary from person to person based on their individual characteristics and predispositions. Mining for patterns of individual-level effect differences, a problem known as heterogeneous treatment effect estimation, has many important applications, from precision medicine to recommender systems. In this paper we define and study a variant of this problem in which an individual-level threshold in treatment needs to be reached, in order to trigger an effect. One of the main contributions of our work is that we do not only estimate heterogeneous treatment effects with fixed treatments but can also prescribe individualized treatments. We propose a tree-based learning method to find the heterogeneity in the treatment effects. Our experimental results on multiple datasets show that our approach can learn the triggers better than existing approaches.