Rishabh Mehrotra

Olivier Jeunen, Ciarán M. Gilligan-Lee, Rishabh Mehrotra et al.

The ability to answer causal questions is crucial in many domains, as causal inference allows one to understand the impact of interventions. In many applications, only a single intervention is possible at a given time. However, in some important areas, multiple interventions are concurrently applied. Disentangling the effects of single interventions from jointly applied interventions is a challenging task -- especially as simultaneously applied interventions can interact. This problem is made harder still by unobserved confounders, which influence both treatments and outcome. We address this challenge by aiming to learn the effect of a single-intervention from both observational data and sets of interventions. We prove that this is not generally possible, but provide identification proofs demonstrating that it can be achieved under non-linear continuous structural causal models with additive, multivariate Gaussian noise -- even when unobserved confounders are present. Importantly, we show how to incorporate observed covariates and learn heterogeneous treatment effects. Based on the identifiability proofs, we provide an algorithm that learns the causal model parameters by pooling data from different regimes and jointly maximizing the combined likelihood. The effectiveness of our method is empirically demonstrated on both synthetic and real-world data.

Sebastin Santy, Prasanta Bhattacharya, Rishabh Mehrotra · uw

With the steady emergence of community question answering (CQA) platforms like Quora, StackExchange, and WikiHow, users now have an unprecedented access to information on various kind of queries and tasks. Moreover, the rapid proliferation and localization of these platforms spanning geographic and linguistic boundaries offer a unique opportunity to study the task requirements and preferences of users in different socio-linguistic groups. In this study, we implement an entity-embedding model trained on a large longitudinal dataset of multi-lingual and task-oriented question-answer pairs to uncover and quantify the (i) prevalence and distribution of various online tasks across linguistic communities, and (ii) emerging and receding trends in task popularity over time in these communities. Our results show that there exists substantial variance in task preference as well as popularity trends across linguistic communities on the platform. Findings from this study will help Q&A platforms better curate and personalize content for non-English users, while also offering valuable insights to businesses looking to target non-English speaking communities online.

Hitesh Sagtani, Madan Jhawar, Rishabh Mehrotra et al.

Ad-load balancing is a critical challenge in online advertising systems, particularly in the context of social media platforms, where the goal is to maximize user engagement and revenue while maintaining a satisfactory user experience. This requires the optimization of conflicting objectives, such as user satisfaction and ads revenue. Traditional approaches to ad-load balancing rely on static allocation policies, which fail to adapt to changing user preferences and contextual factors. In this paper, we present an approach that leverages off-policy learning and evaluation from logged bandit feedback. We start by presenting a motivating analysis of the ad-load balancing problem, highlighting the conflicting objectives between user satisfaction and ads revenue. We emphasize the nuances that arise due to user heterogeneity and the dependence on the user's position within a session. Based on this analysis, we define the problem as determining the optimal ad-load for a particular feed fetch. To tackle this problem, we propose an off-policy learning framework that leverages unbiased estimators such as Inverse Propensity Scoring (IPS) and Doubly Robust (DR) to learn and estimate the policy values using offline collected stochastic data. We present insights from online A/B experiments deployed at scale across over 80 million users generating over 200 million sessions, where we find statistically significant improvements in both user satisfaction metrics and ads revenue for the platform.

Jan Hartman, Rishabh Mehrotra, Hitesh Sagtani et al.

In this work, we discuss a recently popular type of recommender system: an LLM-based coding assistant. Connecting the task of providing code recommendations in multiple formats to traditional RecSys challenges, we outline several similarities and differences due to domain specifics. We emphasize the importance of providing relevant context to an LLM for this use case and discuss lessons learned from context enhancements & offline and online evaluation of such AI-assisted coding systems.

Srijan Saket, Mohit Agarwal, Rishabh Mehrotra

The rise in popularity of social media platforms, has resulted in millions of new, content pieces being created every day. This surge in content creation underscores the need to pay attention to our design choices as they can greatly impact how long content remains relevant. In today's landscape where regularly recommending new content is crucial, particularly in the absence of detailed information, a variety of factors such as UI features, algorithms and system settings contribute to shaping the journey of content across the platform. While previous research has focused on how new content affects users' experiences, this study takes a different approach by analyzing these decisions considering the content itself. Through a series of carefully crafted experiments we explore how seemingly small decisions can influence the longevity of content, measured by metrics like Content Progression (CVP) and Content Survival (CSR). We also emphasize the importance of recognizing the stages that content goes through underscoring the need to tailor strategies for each stage as a one size fits all approach may not be effective. Additionally we argue for a departure from traditional experimental setups in the study of content lifecycles, to avoid potential misunderstandings while proposing advanced techniques, to achieve greater precision and accuracy in the evaluation process.

James McInerney, Brian Brost, Praveen Chandar et al.

Users of music streaming, video streaming, news recommendation, and e-commerce services often engage with content in a sequential manner. Providing and evaluating good sequences of recommendations is therefore a central problem for these services. Prior reweighting-based counterfactual evaluation methods either suffer from high variance or make strong independence assumptions about rewards. We propose a new counterfactual estimator that allows for sequential interactions in the rewards with lower variance in an asymptotically unbiased manner. Our method uses graphical assumptions about the causal relationships of the slate to reweight the rewards in the logging policy in a way that approximates the expected sum of rewards under the target policy. Extensive experiments in simulation and on a live recommender system show that our approach outperforms existing methods in terms of bias and data efficiency for the sequential track recommendations problem.

Brian Brost, Rishabh Mehrotra, Tristan Jehan

At the core of many important machine learning problems faced by online streaming services is a need to model how users interact with the content they are served. Unfortunately, there are no public datasets currently available that enable researchers to explore this topic. In order to spur that research, we release the Music Streaming Sessions Dataset (MSSD), which consists of 160 million listening sessions and associated user actions. Furthermore, we provide audio features and metadata for the approximately 3.7 million unique tracks referred to in the logs. This is the largest collection of such track metadata currently available to the public. This dataset enables research on important problems including how to model user listening and interaction behaviour in streaming, as well as Music Information Retrieval (MIR), and session-based sequential recommendations. Additionally, a subset of sessions were collected using a uniformly random recommendation setting, enabling their use for counterfactual evaluation of such sequential recommendations. Finally, we provide an analysis of user behavior and suggest further research problems which can be addressed using the dataset.

Sebastin Santy, Wazeer Zulfikar, Rishabh Mehrotra et al.

We consider the problem of understanding real world tasks depicted in visual images. While most existing image captioning methods excel in producing natural language descriptions of visual scenes involving human tasks, there is often the need for an understanding of the exact task being undertaken rather than a literal description of the scene. We leverage insights from real world task understanding systems, and propose a framework composed of convolutional neural networks, and an external hierarchical task ontology to produce task descriptions from input images. Detailed experiments highlight the efficacy of the extracted descriptions, which could potentially find their way in many applications, including image alt text generation.

Rishabh Mehrotra, Prasanta Bhattacharya

Video sharing and entertainment websites have rapidly grown in popularity and now constitute some of the most visited websites on the Internet. Despite the active user engagement on these online video-sharing platforms, most of recent research on online media platforms have restricted themselves to networking based social media sites, like Facebook or Twitter. We depart from previous studies in the online media space that have focused exclusively on demand-side user engagement, by modeling the supply-side of the crowd-contributed videos on this platform. The current study is among the first to perform a large-scale empirical study using longitudinal video upload data from a large online video platform. The modeling and subsequent prediction of video uploads is made complicated by the heterogeneity of video types (e.g. popular vs. niche video genres), and the inherent time trend effects associated with media uploads. We identify distinct genre-clusters from our dataset and employ a self-exciting Hawkes point-process model on each of these clusters to fully specify and estimate the video upload process. Additionally, we go beyond prediction to disentangle potential factors that govern user engagement and determine the video upload rates, which improves our analysis with additional explanatory power. Our findings show that using a relatively parsimonious point-process model, we are able to achieve higher model fit, and predict video uploads to the platform with a higher accuracy than competing models. The findings from this study can benefit platform owners in better understanding how their supply-side users engage with their site over time. We also offer a robust method for performing media upload prediction that is likely to be generalizable across media platforms which demonstrate similar temporal and genre-level heterogeneity.

Rishabh Mehrotra, Emine Yilmaz

A significant amount of search queries originate from some real world information need or tasks. In order to improve the search experience of the end users, it is important to have accurate representations of tasks. As a result, significant amount of research has been devoted to extracting proper representations of tasks in order to enable search systems to help users complete their tasks, as well as providing the end user with better query suggestions, for better recommendations, for satisfaction prediction, and for improved personalization in terms of tasks. Most existing task extraction methodologies focus on representing tasks as flat structures. However, tasks often tend to have multiple subtasks associated with them and a more naturalistic representation of tasks would be in terms of a hierarchy, where each task can be composed of multiple (sub)tasks. To this end, we propose an efficient Bayesian nonparametric model for extracting hierarchies of such tasks \& subtasks. We evaluate our method based on real world query log data both through quantitative and crowdsourced experiments and highlight the importance of considering task/subtask hierarchies.

Rishabh Mehrotra, Ashton Anderson, Fernando Diaz et al.

Many online services, such as search engines, social media platforms, and digital marketplaces, are advertised as being available to any user, regardless of their age, gender, or other demographic factors. However, there are growing concerns that these services may systematically underserve some groups of users. In this paper, we present a framework for internally auditing such services for differences in user satisfaction across demographic groups, using search engines as a case study. We first explain the pitfalls of naïvely comparing the behavioral metrics that are commonly used to evaluate search engines. We then propose three methods for measuring latent differences in user satisfaction from observed differences in evaluation metrics. To develop these methods, we drew on ideas from the causal inference literature and the multilevel modeling literature. Our framework is broadly applicable to other online services, and provides general insight into interpreting their evaluation metrics.