arXiv subjects

Ruocheng Guo

Publications and source records attributed to Ruocheng Guo.

At least 73 records · Page 4Linked to original sources

arXiv2021

Out-of-distribution Prediction with Invariant Risk Minimization: The Limitation and An Effective Fix

This work considers the out-of-distribution (OOD) prediction problem where (1)~the training data are from multiple domains and (2)~the test domain is unseen in the training. DNNs fail in OOD prediction because they are prone to pick up spurious correlations. Recently, Invariant Risk Minimization (IRM) is proposed to address this issue. Its effectiveness has been demonstrated in the colored MNIST experiment. Nevertheless, we find that the performance of IRM can be dramatically degraded under \emph{strong $Λ$ spuriousness} -- when the spurious correlation between the spurious features and the class label is strong due to the strong causal influence of their common cause, the domain label, on both of them (see Fig. 1). In this work, we try to answer the questions: why does IRM fail in the aforementioned setting? Why does IRM work for the original colored MNIST dataset? How can we fix this problem of IRM? Then, we propose a simple and effective approach to fix the problem of IRM. We combine IRM with conditional distribution matching to avoid a specific type of spurious correlation under strong $Λ$ spuriousness. Empirically, we design a series of semi synthetic datasets -- the colored MNIST plus, which exposes the problems of IRM and demonstrates the efficacy of the proposed method.

cs.LG↗

arXiv2020

Long-Term Effect Estimation with Surrogate Representation

There are many scenarios where short- and long-term causal effects of an intervention are different. For example, low-quality ads may increase short-term ad clicks but decrease the long-term revenue via reduced clicks. This work, therefore, studies the problem of long-term effect where the outcome of primary interest, or primary outcome, takes months or even years to accumulate. The observational study of long-term effect presents unique challenges. First, the confounding bias causes large estimation error and variance, which can further accumulate towards the prediction of primary outcomes. Second, short-term outcomes are often directly used as the proxy of the primary outcome, i.e., the surrogate. Nevertheless, this method entails the strong surrogacy assumption that is often impractical. To tackle these challenges, we propose to build connections between long-term causal inference and sequential models in machine learning. This enables us to learn surrogate representations that account for the temporal unconfoundedness and circumvent the stringent surrogacy assumption by conditioning on the inferred time-varying confounders. Experimental results show that the proposed framework outperforms the state-of-the-art.

stat.AP↗

arXiv2020

Adversarial Attacks and Defenses: An Interpretation Perspective

Despite the recent advances in a wide spectrum of applications, machine learning models, especially deep neural networks, have been shown to be vulnerable to adversarial attacks. Attackers add carefully-crafted perturbations to input, where the perturbations are almost imperceptible to humans, but can cause models to make wrong predictions. Techniques to protect models against adversarial input are called adversarial defense methods. Although many approaches have been proposed to study adversarial attacks and defenses in different scenarios, an intriguing and crucial challenge remains that how to really understand model vulnerability? Inspired by the saying that "if you know yourself and your enemy, you need not fear the battles", we may tackle the aforementioned challenge after interpreting machine learning models to open the black-boxes. The goal of model interpretation, or interpretable machine learning, is to extract human-understandable terms for the working mechanism of models. Recently, some approaches start incorporating interpretation into the exploration of adversarial attacks and defenses. Meanwhile, we also observe that many existing methods of adversarial attacks and defenses, although not explicitly claimed, can be understood from the perspective of interpretation. In this paper, we review recent work on adversarial attacks and defenses, particularly from the perspective of machine learning interpretation. We categorize interpretation into two types, feature-level interpretation and model-level interpretation. For each type of interpretation, we elaborate on how it could be used for adversarial attacks and defenses. We then briefly illustrate additional correlations between interpretation and adversaries. Finally, we discuss the challenges and future directions along tackling adversary issues with interpretation.

cs.LG↗

arXiv2020

A Survey of Learning Causality with Data: Problems and Methods

This work considers the question of how convenient access to copious data impacts our ability to learn causal effects and relations. In what ways is learning causality in the era of big data different from -- or the same as -- the traditional one? To answer this question, this survey provides a comprehensive and structured review of both traditional and frontier methods in learning causality and relations along with the connections between causality and machine learning. This work points out on a case-by-case basis how big data facilitates, complicates, or motivates each approach.

cs.AI↗

arXiv2020

Understanding and forecasting lifecycle events in information cascades

Most social network sites allow users to reshare a piece of information posted by a user. As time progresses, the cascade of reshares grows, eventually saturating after a certain time period. While previous studies have focused heavily on one aspect of the cascade phenomenon, specifically predicting when the cascade would go viral, in this paper, we take a more holistic approach by analyzing the occurrence of two events within the cascade lifecycle - the period of maximum growth in terms of surge in reshares and the period where the cascade starts declining in adoption. We address the challenges in identifying these periods and then proceed to make a comparative analysis of these periods from the perspective of network topology. We study the effect of several node-centric structural measures on the reshare responses using Granger causality which helps us quantify the significance of the network measures and understand the extent to which the network topology impacts the growth dynamics. This evaluation is performed on a dataset of 7407 cascades extracted from the Weibo social network. Using our causality framework, we found that an entropy measure based on nodal degree causally affects the occurrence of these events in 93.95% of cascades. Surprisingly, this outperformed clustering coefficient and PageRank which we hypothesized would be more indicative of the growth dynamics based on earlier studies. We also extend the Granger-causality Vector Autoregression (VAR) model to forecast the times at which the events occur in the cascade lifecycle.

cs.SI↗

arXiv2020

Causal Interpretability for Machine Learning -- Problems, Methods and Evaluation

Machine learning models have had discernible achievements in a myriad of applications. However, most of these models are black-boxes, and it is obscure how the decisions are made by them. This makes the models unreliable and untrustworthy. To provide insights into the decision making processes of these models, a variety of traditional interpretable models have been proposed. Moreover, to generate more human-friendly explanations, recent work on interpretability tries to answer questions related to causality such as "Why does this model makes such decisions?" or "Was it a specific feature that caused the decision made by the model?". In this work, models that aim to answer causal questions are referred to as causal interpretable models. The existing surveys have covered concepts and methodologies of traditional interpretability. In this work, we present a comprehensive survey on causal interpretable models from the aspects of the problems and methods. In addition, this survey provides in-depth insights into the existing evaluation metrics for measuring interpretability, which can help practitioners understand for what scenarios each evaluation metric is suitable.

cs.LG↗

arXiv2019

Counterfactual Evaluation of Treatment Assignment Functions with Networked Observational Data

Counterfactual evaluation of novel treatment assignment functions (e.g., advertising algorithms and recommender systems) is one of the most crucial causal inference problems for practitioners. Traditionally, randomized controlled trials (A/B tests) are performed to evaluate treatment assignment functions. However, such trials can be time-consuming, expensive, and even unethical in some cases. Therefore, offline counterfactual evaluation of treatment assignment functions becomes a pressing issue because a massive amount of observational data is available in today's big data era. Counterfactual evaluation requires handling the hidden confounders -- the unmeasured features which causally influence both the treatment assignment and the outcome. To deal with the hidden confounders, most of the existing methods rely on the assumption of no hidden confounders. However, this assumption can be untenable in the context of massive observational data. When such data comes with network information, the later can be potentially useful to correct hidden confounding bias. As such, we first formulate a novel problem, counterfactual evaluation of treatment assignment functions with networked observational data. Then, we investigate the following research questions: How can we utilize network information in counterfactual evaluation? Can network information improve the estimates in counterfactual evaluation? Toward answering these questions, first, we propose a novel framework, \emph{Counterfactual Network Evaluator} (CONE), which (1) learns partial representations of latent confounders under the supervision of observed treatments and outcomes; and (2) combines them for counterfactual evaluation. Then through extensive experiments, we corroborate the effectiveness of CONE. The results imply that incorporating network information mitigates hidden confounding bias in counterfactual evaluation.

cs.LG↗

arXiv2019

Learning Individual Causal Effects from Networked Observational Data

Convenient access to observational data enables us to learn causal effects without randomized experiments. This research direction draws increasing attention in research areas such as economics, healthcare, and education. For example, we can study how a medicine (the treatment) causally affects the health condition (the outcome) of a patient using existing electronic health records. To validate causal effects learned from observational data, we have to control confounding bias -- the influence of variables which causally influence both the treatment and the outcome. Existing work along this line overwhelmingly relies on the unconfoundedness assumption that there do not exist unobserved confounders. However, this assumption is untestable and can even be untenable. In fact, an important fact ignored by the majority of previous work is that observational data can come with network information that can be utilized to infer hidden confounders. For example, in an observational study of the individual-level treatment effect of a medicine, instead of randomized experiments, the medicine is often assigned to each individual based on a series of factors. Some of the factors (e.g., socioeconomic status) can be challenging to measure and therefore become hidden confounders. Fortunately, the socioeconomic status of an individual can be reflected by whom she is connected in social networks. With this fact in mind, we aim to exploit the network information to recognize patterns of hidden confounders which would further allow us to learn valid individual causal effects from observational data. In this work, we propose a novel causal inference framework, the network deconfounder, which learns representations to unravel patterns of hidden confounders from the network information. Empirically, we perform extensive experiments to validate the effectiveness of the network deconfounder on various datasets.

cs.SI↗

arXiv2019

Privacy-Aware Recommendation with Private-Attribute Protection using Adversarial Learning

Recommendation is one of the critical applications that helps users find information relevant to their interests. However, a malicious attacker can infer users' private information via recommendations. Prior work obfuscates user-item data before sharing it with recommendation system. This approach does not explicitly address the quality of recommendation while performing data obfuscation. Moreover, it cannot protect users against private-attribute inference attacks based on recommendations. This work is the first attempt to build a Recommendation with Attribute Protection (RAP) model which simultaneously recommends relevant items and counters private-attribute inference attacks. The key idea of our approach is to formulate this problem as an adversarial learning problem with two main components: the private attribute inference attacker, and the Bayesian personalized recommender. The attacker seeks to infer users' private-attribute information according to their items list and recommendations. The recommender aims to extract users' interests while employing the attacker to regularize the recommendation process. Experiments show that the proposed model both preserves the quality of recommendation service and protects users against private-attribute inference attacks.

cs.SI↗

arXiv2019

I Am Not What I Write: Privacy Preserving Text Representation Learning

Online users generate tremendous amounts of textual information by participating in different activities, such as writing reviews and sharing tweets. This textual data provides opportunities for researchers and business partners to study and understand individuals. However, this user-generated textual data not only can reveal the identity of the user but also may contain individual's private information (e.g., age, location, gender). Hence, "you are what you write" as the saying goes. Publishing the textual data thus compromises the privacy of individuals who provided it. The need arises for data publishers to protect people's privacy by anonymizing the data before publishing it. It is challenging to design effective anonymization techniques for textual information which minimizes the chances of re-identification and does not contain users' sensitive information (high privacy) while retaining the semantic meaning of the data for given tasks (high utility). In this paper, we study this problem and propose a novel double privacy preserving text representation learning framework, DPText, which learns a textual representation that (1) is differentially private, (2) does not contain private information and (3) retains high utility for the given task. Evaluating on two natural language processing tasks, i.e., sentiment analysis and part of speech tagging, we show the effectiveness of this approach in terms of preserving both privacy and utility.

cs.CR↗

arXiv2019

Detecting Pathogenic Social Media Accounts without Content or Network Structure

The spread of harmful mis-information in social media is a pressing problem. We refer accounts that have the capability of spreading such information to viral proportions as "Pathogenic Social Media" accounts. These accounts include terrorist supporters accounts, water armies, and fake news writers. We introduce an unsupervised causality-based framework that also leverages label propagation. This approach identifies these users without using network structure, cascade path information, content and user's information. We show our approach obtains higher precision (0.75) in identifying Pathogenic Social Media accounts in comparison with random (precision of 0.11) and existing bot detection (precision of 0.16) methods.

cs.SI↗

arXiv2019

Using network motifs to characterize temporal network evolution leading to diffusion inhibition

Network motifs are patterns of over-represented node interactions in a network which have been previously used as building blocks to understand various aspects of the social networks. In this paper, we use motif patterns to characterize the information diffusion process in social networks. We study the lifecycle of information cascades to understand what leads to saturation of growth in terms of cascade reshares, thereby resulting in expiration, an event we call ``diffusion inhibition''. In an attempt to understand what causes inhibition, we use motifs to dissect the network obtained from information cascades coupled with traces of historical diffusion or social network links. Our main results follow from experiments on a dataset of cascades from the Weibo platform and the Flixster movie ratings. We observe the temporal counts of 5-node undirected motifs from the cascade temporal networks leading to the inhibition stage. Empirical evidences from the analysis lead us to conclude the following about stages preceding inhibition: (1) individuals tend to adopt information more from users they have known in the past through social networks or previous interactions thereby creating patterns containing triads more frequently than acyclic patterns with linear chains and (2) users need multiple exposures or rounds of social reinforcement for them to adopt an information and as a result information starts spreading slowly thereby leading to the death of the cascade. Following these observations, we use motif based features to predict the edge cardinality of the network exhibited at the time of inhibition. We test features of motif patterns by using regression models for both individual patterns and their combination and we find that motifs as features are better predictors of the future network organization than individual node centralities.

cs.SI↗

arXiv2018

Protecting User Privacy: An Approach for Untraceable Web Browsing History and Unambiguous User Profiles

The overturning of the Internet Privacy Rules by the Federal Communications Commissions (FCC) in late March 2017 allows Internet Service Providers (ISPs) to collect, share and sell their customers' Web browsing data without their consent. With third-party trackers embedded on Web pages, this new rule has put user privacy under more risk. The need arises for users on their own to protect their Web browsing history from any potential adversaries. Although some available solutions such as Tor, VPN, and HTTPS can help users conceal their online activities, their use can also significantly hamper personalized online services, i.e., degraded utility. In this paper, we design an effective Web browsing history anonymization scheme, PBooster, aiming to protect users' privacy while retaining the utility of their Web browsing history. The proposed model pollutes users' Web browsing history by automatically inferring how many and what links should be added to the history while addressing the utility-privacy trade-off challenge. We conduct experiments to validate the quality of the manipulated Web browsing history and examine the robustness of the proposed approach for user privacy protection.

cs.CR↗

arXiv2018

Linked Causal Variational Autoencoder for Inferring Paired Spillover Effects

Modeling spillover effects from observational data is an important problem in economics, business, and other fields of research. % It helps us infer the causality between two seemingly unrelated set of events. For example, if consumer spending in the United States declines, it has spillover effects on economies that depend on the U.S. as their largest export market. In this paper, we aim to infer the causation that results in spillover effects between pairs of entities (or units), we call this effect as \textit{paired spillover}. To achieve this, we leverage the recent developments in variational inference and deep learning techniques to propose a generative model called Linked Causal Variational Autoencoder (LCVA). Similar to variational autoencoders (VAE), LCVA incorporates an encoder neural network to learn the latent attributes and a decoder network to reconstruct the inputs. However, unlike VAE, LCVA treats the \textit{latent attributes as confounders that are assumed to affect both the treatment and the outcome of units}. Specifically, given a pair of units $u$ and $\bar{u}$, their individual treatment and outcomes, the encoder network of LCVA samples the confounders by conditioning on the observed covariates of $u$, the treatments of both $u$ and $\bar{u}$ and the outcome of $u$. Once inferred, the latent attributes (or confounders) of $u$ captures the spillover effect of $\bar{u}$ on $u$. Using a network of users from job training dataset (LaLonde (1986)) and co-purchase dataset from Amazon e-commerce domain, we show that LCVA is significantly more robust than existing methods in capturing spillover effects.

cs.LG↗

arXiv2018

Strongly Hierarchical Factorization Machines and ANOVA Kernel Regression

High-order parametric models that include terms for feature interactions are applied to various data mining tasks, where ground truth depends on interactions of features. However, with sparse data, the high- dimensional parameters for feature interactions often face three issues: expensive computation, difficulty in parameter estimation and lack of structure. Previous work has proposed approaches which can partially re- solve the three issues. In particular, models with factorized parameters (e.g. Factorization Machines) and sparse learning algorithms (e.g. FTRL-Proximal) can tackle the first two issues but fail to address the third. Regarding to unstructured parameters, constraints or complicated regularization terms are applied such that hierarchical structures can be imposed. However, these methods make the optimization problem more challenging. In this work, we propose Strongly Hierarchical Factorization Machines and ANOVA kernel regression where all the three issues can be addressed without making the optimization problem more difficult. Experimental results show the proposed models significantly outperform the state-of-the-art in two data mining tasks: cold-start user response time prediction and stock volatility prediction.

cs.LG↗

arXiv2017

Temporal Analysis of Influence to Predict Users' Adoption in Online Social Networks

Different measures have been proposed to predict whether individuals will adopt a new behavior in online social networks, given the influence produced by their neighbors. In this paper, we show one can achieve significant improvement over these standard measures, extending them to consider a pair of time constraints. These constraints provide a better proxy for social influence, showing a stronger correlation to the probability of influence as well as the ability to predict influence.

cs.SI↗

arXiv2016

Toward Early and Order-of-Magnitude Cascade Prediction in Social Networks

When a piece of information (microblog, photograph, video, link, etc.) starts to spread in a social network, an important question arises: will it spread to viral proportions - where viral can be defined as an order-of-magnitude increase. However, several previous studies have established that cascade size and frequency are related through a power-law - which leads to a severe imbalance in this classification problem. In this paper, we devise a suite of measurements based on structural diversity - the variety of social contexts (communities) in which individuals partaking in a given cascade engage. We demonstrate these measures are able to distinguish viral from non-viral cascades, despite the severe imbalance of the data for this problem. Further, we leverage these measurements as features in a classification approach, successfully predicting microblogs that grow from 50 to 500 reposts with precision of 0.69 and recall of 0.52 for the viral class - despite this class comprising under 2% of samples. This significantly outperforms our baseline approach as well as the current state-of-the-art. We also show this approach also performs well for identifying if cascades observed for 60 minutes will grow to 500 reposts as well as demonstrate how we can tradeoff between precision and recall.

cs.SI↗

arXiv2016

An Empirical Evaluation Of Social Influence Metrics

Predicting when an individual will adopt a new behavior is an important problem in application domains such as marketing and public health. This paper examines the perfor- mance of a wide variety of social network based measurements proposed in the literature - which have not been previously compared directly. We study the probability of an individual becoming influenced based on measurements derived from neigh- borhood (i.e. number of influencers, personal network exposure), structural diversity, locality, temporal measures, cascade mea- sures, and metadata. We also examine the ability to predict influence based on choice of classifier and how the ratio of positive to negative samples in both training and testing affect prediction results - further enabling practical use of these concepts for social influence applications.

cs.SI↗