arXiv subjects

Xiaolin Shi

Publications and source records attributed to Xiaolin Shi.

14 recordsLinked to original sources

arXiv2026

ELICITED: EHR-grounded Longitudinal Interactive Conversations for Information-seeking Triage Evaluation and Decision-making

Emergency-department (ED) triage requires clinicians to rapidly identify patients who need immediate attention, determine who can safely wait, and prioritize limited clinical resources. At presentation, however, information may be limited to a chief complaint and initial vital signs. Clinically important details, including symptom onset and progression, associated symptoms, medical history, and medication use, are often obtained through focused conversation. Effective triage therefore requires clinicians to identify information gaps, ask appropriate follow-up questions, and update their assessment as new evidence becomes available. Most existing ED benchmarks evaluate acuity prediction from a fixed clinical snapshot. Although this formulation measures predictive performance after patient information has been assembled, it does not capture the interactive process through which triage-relevant evidence is elicited and interpreted. Existing medical dialogue datasets support the study of clinical communication, but dialogue statements are not always linked to temporally ordered events in the electronic health record (EHR). We introduce EHR2Dial-Triage, an agentic conversation-generation framework and benchmark grounded in MIMIC-IV-ED. The framework constructs triage conversations under explicit role-based and temporal information boundaries. Each accepted patient disclosure is linked to its supporting EHR event and the first dialogue turn at which it becomes available. EHR2Dial-Triage enables controlled evaluation of information elicitation, evidence use, five-level Emergency Severity Index prediction, and patient-facing communication across models and patient personas. It provides a structured setting for studying conversational triage as a dynamic process of clinical information acquisition, reasoning, and communication.

cs.CL↗

arXiv2023

Balancing Approach for Causal Inference at Scale

With the modern software and online platforms to collect massive amount of data, there is an increasing demand of applying causal inference methods at large scale when randomized experimentation is not viable. Weighting methods that directly incorporate covariate balancing have recently gained popularity for estimating causal effects in observational studies. These methods reduce the manual efforts required by researchers to iterate between propensity score modeling and balance checking until a satisfied covariate balance result. However, conventional solvers for determining weights lack the scalability to apply such methods on large scale datasets in companies like Snap Inc. To address the limitations and improve computational efficiency, in this paper we present scalable algorithms, DistEB and DistMS, for two balancing approaches: entropy balancing and MicroSynth. The solvers have linear time complexity and can be conveniently implemented in distributed computing frameworks such as Spark, Hive, etc. We study the properties of balancing approaches at different scales up to 1 million treated units and 487 covariates. We find that with larger sample size, both bias and variance in the causal effect estimation are significantly reduced. The results emphasize the importance of applying balancing approaches on large scale datasets. We combine the balancing approach with a synthetic control framework and deploy an end-to-end system for causal impact estimation at Snap Inc.

stat.ME↗

arXiv2023

Cultural Differences in Friendship Network Behaviors: A Snapchat Case Study

Culture shapes people's behavior, both online and offline. Surprisingly, there is sparse research on how cultural context affects network formation and content consumption on social media. We analyzed the friendship networks and dyadic relations between content producers and consumers across 73 countries through a cultural lens in a closed-network setting. Closed networks allow for intimate bonds and self-expression, providing a natural setting to study cultural differences in behavior. We studied three theoretical frameworks of culture - individualism, relational mobility, and tightness. We found that friendship networks formed across different cultures differ in egocentricity, meaning the connectedness between a user's friends. Individualism, mobility, and looseness also significantly negatively impact how tie strength affects content consumption. Our findings show how culture affects social media behavior, and we outline how researchers can incorporate this in their work. Our work has implications for content recommendations and can improve content engagement.

cs.SI↗

arXiv2021

Semi-simplicity of Temperley-Lieb Algebras of type D

We provide a necessary and sufficient condition for a type D Temperley-Lieb algebra ${\rm TLD}_n(δ)$ being semi-simple by studying branching rule for cell modules. As a byproduct, our result is used to study the so-called forked Temperley-Lieb algebra, which is a quotient algebra of ${\rm TLD}_n(δ)$.

math.RT↗

arXiv2020

How to Measure Your App: A Couple of Pitfalls and Remedies in Measuring App Performance in Online Controlled Experiments

Effectively measuring, understanding, and improving mobile app performance is of paramount importance for mobile app developers. Across the mobile Internet landscape, companies run online controlled experiments (A/B tests) with thousands of performance metrics in order to understand how app performance causally impacts user retention and to guard against service or app regressions that degrade user experiences. To capture certain characteristics particular to performance metrics, such as enormous observation volume and high skewness in distribution, an industry-standard practice is to construct a performance metric as a quantile over all performance events in control or treatment buckets in A/B tests. In our experience with thousands of A/B tests provided by Snap, we have discovered some pitfalls in this industry-standard way of calculating performance metrics that can lead to unexplained movements in performance metrics and unexpected misalignment with user engagement metrics. In this paper, we discuss two major pitfalls in this industry-standard practice of measuring performance for mobile apps. One arises from strong heterogeneity in both mobile devices and user engagement, and the other arises from self-selection bias caused by post-treatment user engagement changes. To remedy these two pitfalls, we introduce several scalable methods including user-level performance metric calculation and imputation and matching for missing metric values. We have extensively evaluated these methods on both simulation data and real A/B tests, and have deployed them into Snap's in-house experimentation platform.

stat.AP↗

arXiv2020

Knowing your FATE: Friendship, Action and Temporal Explanations for User Engagement Prediction on Social Apps

With the rapid growth and prevalence of social network applications (Apps) in recent years, understanding user engagement has become increasingly important, to provide useful insights for future App design and development. While several promising neural modeling approaches were recently pioneered for accurate user engagement prediction, their black-box designs are unfortunately limited in model explainability. In this paper, we study a novel problem of explainable user engagement prediction for social network Apps. First, we propose a flexible definition of user engagement for various business scenarios, based on future metric expectations. Next, we design an end-to-end neural framework, FATE, which incorporates three key factors that we identify to influence user engagement, namely friendships, user actions, and temporal dynamics to achieve explainable engagement predictions. FATE is based on a tensor-based graph neural network (GNN), LSTM and a mixture attention mechanism, which allows for (a) predictive explanations based on learned weights across different feature categories, (b) reduced network complexity, and (c) improved performance in both prediction accuracy and training/inference time. We conduct extensive experiments on two large-scale datasets from Snapchat, where FATE outperforms state-of-the-art approaches by ${\approx}10\%$ error and ${\approx}20\%$ runtime reduction. We also evaluate explanations from FATE, showing strong quantitative and qualitative performance.

cs.SI↗

arXiv2019

I Know You'll Be Back: Interpretable New User Clustering and Churn Prediction on a Mobile Social Application

As online platforms are striving to get more users, a critical challenge is user churn, which is especially concerning for new users. In this paper, by taking the anonymous large-scale real-world data from Snapchat as an example, we develop \textit{ClusChurn}, a systematic two-step framework for interpretable new user clustering and churn prediction, based on the intuition that proper user clustering can help understand and predict user churn. Therefore, \textit{ClusChurn} firstly groups new users into interpretable typical clusters, based on their activities on the platform and ego-network structures. Then we design a novel deep learning pipeline based on LSTM and attention to accurately predict user churn with very limited initial behavior data, by leveraging the correlations among users' multi-dimensional activities and the underlying user types. \textit{ClusChurn} is also able to predict user types, which enables rapid reactions to different types of user churn. Extensive data analysis and experiments show that \textit{ClusChurn} provides valuable insight into user behaviors, and achieves state-of-the-art churn prediction performance. The whole framework is deployed as a data analysis pipeline, delivering real-time data analysis and prediction results to multiple relevant teams for business intelligence uses. It is also general enough to be readily adopted by any online systems with user behavior data.

cs.SI↗

arXiv2019

Characterizing and Forecasting User Engagement with In-app Action Graph: A Case Study of Snapchat

While mobile social apps have become increasingly important in people's daily life, we have limited understanding on what motivates users to engage with these apps. In this paper, we answer the question whether users' in-app activity patterns help inform their future app engagement (e.g., active days in a future time window)? Previous studies on predicting user app engagement mainly focus on various macroscopic features (e.g., time-series of activity frequency), while ignoring fine-grained inter-dependencies between different in-app actions at the microscopic level. Here we propose to formalize individual user's in-app action transition patterns as a temporally evolving action graph, and analyze its characteristics in terms of informing future user engagement. Our analysis suggested that action graphs are able to characterize user behavior patterns and inform future engagement. We derive a number of high-order graph features to capture in-app usage patterns and construct interpretable models for predicting trends of engagement changes and active rates. To further enhance predictive power, we design an end-to-end, multi-channel neural model to encode temporal action graphs, activity sequences, and other macroscopic features. Experiments on predicting user engagement for 150k Snapchat new users over a 28-day period demonstrate the effectiveness of the proposed models. The prediction framework is deployed at Snapchat to deliver real world business insights. Our proposed framework is also general and can be applied to other social app platforms.

cs.LG↗

arXiv2018

False Discovery Rate Controlled Heterogeneous Treatment Effect Detection for Online Controlled Experiments

Online controlled experiments (a.k.a. A/B testing) have been used as the mantra for data-driven decision making on feature changing and product shipping in many Internet companies. However, it is still a great challenge to systematically measure how every code or feature change impacts millions of users with great heterogeneity (e.g. countries, ages, devices). The most commonly used A/B testing framework in many companies is based on Average Treatment Effect (ATE), which cannot detect the heterogeneity of treatment effect on users with different characteristics. In this paper, we propose statistical methods that can systematically and accurately identify Heterogeneous Treatment Effect (HTE) of any user cohort of interest (e.g. mobile device type, country), and determine which factors (e.g. age, gender) of users contribute to the heterogeneity of the treatment effect in an A/B test. By applying these methods on both simulation data and real-world experimentation data, we show how they work robustly with controlled low False Discover Rate (FDR), and at the same time, provides us with useful insights about the heterogeneity of identified user groups. We have deployed a toolkit based on these methods, and have used it to measure the Heterogeneous Treatment Effect of many A/B tests at Snap.

stat.AP↗

arXiv2016

A Framework for Network AB Testing

A/B testing, also known as controlled experiment, bucket testing or splitting testing, has been widely used for evaluating a new feature, service or product in the data-driven decision processes of online websites. The goal of A/B testing is to estimate or test the difference between the treatment effects of the old and new variations. It is a well-studied two-sample comparison problem if each user's response is influenced by her treatment only. However, in many applications of A/B testing, especially those in HIVE of Yahoo and other social networks of Microsoft, Facebook, LinkedIn, Twitter and Google, users in the social networks influence their friends via underlying social interactions, and the conventional A/B testing methods fail to work. This paper considers the network A/B testing problem and provide a general framework consisting of five steps: data sampling, probabilistic model, parameter inference, computing average treatment effect and hypothesis test. The framework performs well for network A/B testing in simulation studies.

stat.AP↗

arXiv2010

Citing for High Impact

The question of citation behavior has always intrigued scientists from various disciplines. While general citation patterns have been widely studied in the literature we develop the notion of citation projection graphs by investigating the citations among the publications that a given paper cites. We investigate how patterns of citations vary between various scientific disciplines and how such patterns reflect the scientific impact of the paper. We find that idiosyncratic citation patterns are characteristic for low impact papers; while narrow, discipline-focused citation patterns are common for medium impact papers. Our results show that crossing-community, or bridging citation patters are high risk and high reward since such patterns are characteristic for both low and high impact papers. Last, we observe that recently citation networks are trending toward more bridging and interdisciplinary forms.

cs.DL↗

arXiv2009

Information Diffusion in Computer Science Citation Networks

The paper citation network is a traditional social medium for the exchange of ideas and knowledge. In this paper we view citation networks from the perspective of information diffusion. We study the structural features of the information paths through the citation networks of publications in computer science, and analyze the impact of various citation choices on the subsequent impact of the article. We find that citing recent papers and papers within the same scholarly community garners a slightly larger number of citations on average. However, this correlation is weaker among well-cited papers implying that for high impact work citing within one's field is of lesser importance. We also study differences in information flow for specific subsets of citation networks: books versus conference and journal articles, different areas of computer science, and different time periods.

cs.DL↗

arXiv2007

Scatter Networks: A New Approach for Analyzing Information Scatter on the Web

Information on any given topic is often scattered across the web. Previously this scatter has been characterized through the distribution of a set of facts (i.e. pieces of information) across web pages, showing that typically a few pages contain many facts on the topic, while many pages contain just a few. While such approaches have revealed important scatter phenomena, they are lossy in that they conceal how specific facts (e.g. rare facts) occur in specific types of pages (e.g. fact-rich pages). To reveal such regularities, we construct bi-partite networks, consisting of two types of vertices: the facts contained in webpages and the webpages themselves. Such a representation enables the application of a series of network analysis techniques, revealing structural features such as connectivity, robustness, and clustering. We discuss the implications of each of these features to the users' ability to find comprehensive information online. Finally, we compare the bipartite graph structure of webpages and facts with the hyperlink structure between the webpages.

cs.IR↗

arXiv2006

Networks of strong ties

Social networks transmitting covert or sensitive information cannot use all ties for this purpose. Rather, they can only use a subset of ties that are strong enough to be ``trusted''. In this paper we consider transitivity as evidence of strong ties, requiring that each tie can only be used if the individuals on either end also share at least one other contact in common. We examine the effect of removing all non-transitive ties in two real social network data sets. We observe that although some individuals become disconnected, a giant connected component remains, with an average shortest path only slightly longer than that of the original network. We also evaluate the cost of forming transitive ties by deriving the conditions for the emergence and the size of the giant component in a random graph composed entirely of closed triads and the equivalent Erdos-Renyi random graph.

cond-mat.stat-mech↗