BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Ee-Peng Lim

Ee-Peng Lim appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Social and Information NetworksMachine LearningComputer VisionInformation Retrievalcs.CYMultimediaComputation and LanguageData Structures and AlgorithmsDatabasesphysics.soc-ph

Catalog footprint

What is connected

14works
10topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

14 published item(s)

preprint2026arXiv

Towards Unbiased Cross-Modal Representation Learning for Food Image-to-Recipe Retrieval

This paper addresses the challenges of learning representations for recipes and food images in the cross-modal retrieval problem. As the relationship between a recipe and its cooked dish is cause-and-effect, treating a recipe as a text source describing the visual appearance of a dish for learning representation, as the existing approaches, will create bias misleading image-and-recipe similarity judgment. Specifically, a food image may not equally capture every detail in a recipe, due to factors such as the cooking process, dish presentation, and image-capturing conditions. The current representation learning tends to capture dominant visual-text alignment while overlooking subtle variations that determine retrieval relevance. In this paper, we model such bias in cross-modal representation learning using causal theory. The causal view of this problem suggests ingredients as one of the confounder sources and a simple backdoor adjustment can alleviate the bias. By causal intervention, we reformulate the conventional model for food-to-recipe retrieval with an additional term to remove the potential bias in similarity judgment. Based on this theory-informed formulation, we empirically prove the oracle performance of retrieval on the Recipe1M dataset to be MedR=1 across the testing data sizes of 1K, 10K, and even 50K. We also propose a plug-and-play neural module, which is essentially a multi-label ingredient classifier for debiasing. New state-of-the-art search performances are reported on the Recipe1M dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems

Large language model-driven multi-agent systems (LLM-MAS) excel at complex tasks, yet unreliable agents remain a key bottleneck to system-level reliability. Automatic failure attribution is therefore critical, but existing approaches, such as direct prediction of agent-error pairs and agent-first failure attribution, rely on local logs of agents and miss global failures that only manifest over full interaction trajectories, such as cross-step inconsistencies and inter-agent coordination errors. Moreover, directly predicting failures induces a large combinatorial search space, hindering fine-grained attribution. To address these challenges, we propose VerifyMAS, a hypothesis verification framework for agent failure attribution. Instead of directly predicting faulty agents and error types, VerifyMAS formulates and verifies failure hypotheses against full trajectories. This verification-based approach decomposes attribution into trajectory-level error validation and fine-grained agent localization, providing an error-first attribution approach that captures global failure patterns while substantially reducing the search space. We further introduce a hypothesis-based data construction strategy grounded in a structured error taxonomy and fine-tune a specialized LLM verifier model for trajectory-level failure verification and agent attribution. Experiments on Aegis-Bench and Who&When show that VerifyMAS consistently improves diverse backbone models, including open-source Qwen and API-based GPT models, outperforming prior methods without sacrificing inference efficiency for long multi-agent trajectories.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Near-Optimal Change-Detection Based Algorithm for Piecewise-Stationary Combinatorial Semi-Bandits

We investigate the piecewise-stationary combinatorial semi-bandit problem. Compared to the original combinatorial semi-bandit problem, our setting assumes the reward distributions of base arms may change in a piecewise-stationary manner at unknown time steps. We propose an algorithm, \texttt{GLR-CUCB}, which incorporates an efficient combinatorial semi-bandit algorithm, \texttt{CUCB}, with an almost parameter-free change-point detector, the \emph{Generalized Likelihood Ratio Test} (GLRT). Our analysis shows that the regret of \texttt{GLR-CUCB} is upper bounded by $\mathcal{O}(\sqrt{NKT\log{T}})$, where $N$ is the number of piecewise-stationary segments, $K$ is the number of base arms, and $T$ is the number of time steps. As a complement, we also derive a nearly matching regret lower bound on the order of $Ω(\sqrt{NKT}$), for both piecewise-stationary multi-armed bandits and combinatorial semi-bandits, using information-theoretic techniques and judiciously constructed piecewise-stationary bandit instances. Our lower bound is tighter than the best available regret lower bound, which is $Ω(\sqrt{T})$. Numerical experiments on both synthetic and real-world datasets demonstrate the superiority of \texttt{GLR-CUCB} compared to other state-of-the-art algorithms.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Face to Purchase: Predicting Consumer Choices with Structured Facial and Behavioral Traits Embedding

Predicting consumers' purchasing behaviors is critical for targeted advertisement and sales promotion in e-commerce. Human faces are an invaluable source of information for gaining insights into consumer personality and behavioral traits. However, consumer's faces are largely unexplored in previous research, and the existing face-related studies focus on high-level features such as personality traits while neglecting the business significance of learning from facial data. We propose to predict consumers' purchases based on their facial features and purchasing histories. We design a semi-supervised model based on a hierarchical embedding network to extract high-level features of consumers and to predict the top-$N$ purchase destinations of a consumer. Our experimental results on a real-world dataset demonstrate the positive effect of incorporating facial information in predicting consumers' purchasing behaviors.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

JPLink: On Linking Jobs to Vocational Interest Types

Linking job seekers with relevant jobs requires matching based on not only skills, but also personality types. Although the Holland Code also known as RIASEC has frequently been used to group people by their suitability for six different categories of occupations, the RIASEC category labels of individual jobs are often not found in job posts. This is attributed to significant manual efforts required for assigning job posts with RIASEC labels. To cope with assigning massive number of jobs with RIASEC labels, we propose JPLink, a machine learning approach using the text content in job titles and job descriptions. JPLink exploits domain knowledge available in an occupation-specific knowledge base known as O*NET to improve feature representation of job posts. To incorporate relative ranking of RIASEC labels of each job, JPLink proposes a listwise loss function inspired by learning to rank. Both our quantitative and qualitative evaluations show that JPLink outperforms conventional baselines. We conduct an error analysis on JPLink's predictions to show that it can uncover label errors in existing job posts.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

On Predicting Personal Values of Social Media Users using Community-Specific Language Features and Personal Value Correlation

Personal values have significant influence on individuals' behaviors, preferences, and decision making. It is therefore not a surprise that personal values of a person could influence his or her social media content and activities. Instead of getting users to complete personal value questionnaire, researchers have looked into a non-intrusive and highly scalable approach to predict personal values using user-generated social media data. Nevertheless, geographical differences in word usage and profile information are issues to be addressed when designing such prediction models. In this work, we focus on analyzing Singapore users' personal values, and developing effective models to predict their personal values using their Facebook data. These models leverage on word categories in Linguistic Inquiry and Word Count (LIWC) and correlations among personal values. The LIWC word categories are adapted to non-English word use in Singapore. We incorporate the correlations among personal values into our proposed Stack Model consisting of a task-specific layer of base models and a cross-stitch layer model. Through experiments, we show that our proposed model predicts personal values with considerable improvement of accuracy over the previous works. Moreover, we use the stack model to predict the personal values of a large community of Twitter users using their public tweet content and empirically derive several interesting findings about their online behavior consistent with earlier findings in the social science and social media literature.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Learning Cross-Modal Embeddings with Adversarial Networks for Cooking Recipes and Food Images

Food computing is playing an increasingly important role in human daily life, and has found tremendous applications in guiding human behavior towards smart food consumption and healthy lifestyle. An important task under the food-computing umbrella is retrieval, which is particularly helpful for health related applications, where we are interested in retrieving important information about food (e.g., ingredients, nutrition, etc.). In this paper, we investigate an open research task of cross-modal retrieval between cooking recipes and food images, and propose a novel framework Adversarial Cross-Modal Embedding (ACME) to resolve the cross-modal retrieval task in food domains. Specifically, the goal is to learn a common embedding feature space between the two modalities, in which our approach consists of several novel ideas: (i) learning by using a new triplet loss scheme together with an effective sampling strategy, (ii) imposing modality alignment using an adversarial learning strategy, and (iii) imposing cross-modal translation consistency such that the embedding of one modality is able to recover some important information of corresponding instances in the other modality. ACME achieves the state-of-the-art performance on the benchmark Recipe1M dataset, validating the efficacy of the proposed technique.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

A Business Zone Recommender System Based on Facebook and Urban Planning Data

We present ZoneRec---a zone recommendation system for physical businesses in an urban city, which uses both public business data from Facebook and urban planning data. The system consists of machine learning algorithms that take in a business' metadata and outputs a list of recommended zones to establish the business in. We evaluate our system using data of food businesses in Singapore and assess the contribution of different feature groups to the recommendation quality.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

CareerMapper: An Automated Resume Evaluation Tool

The advent of the Web brought about major changes in the way people search for jobs and companies look for suitable candidates. As more employers and recruitment firms turn to the Web for job candidate search, an increasing number of people turn to the Web for uploading and creating their online resumes. Resumes are often the first source of information about candidates and also the first item of evaluation in candidate selection. Thus, it is imperative that resumes are complete, free of errors and well-organized. We present an automated resume evaluation tool called "CareerMapper". Our tool is designed to conduct a thorough review of a user's LinkedIn profile and provide best recommendations for improved online resumes by analyzing a large number of online user profiles.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Collective Semi-Supervised Learning for User Profiling in Social Media

The abundance of user-generated data in social media has incentivized the development of methods to infer the latent attributes of users, which are crucially useful for personalization, advertising and recommendation. However, the current user profiling approaches have limited success, due to the lack of a principled way to integrate different types of social relationships of a user, and the reliance on scarcely-available labeled data in building a prediction model. In this paper, we present a novel solution termed Collective Semi-Supervised Learning (CSL), which provides a principled means to integrate different types of social relationship and unlabeled data under a unified computational framework. The joint learning from multiple relationships and unlabeled data yields a computationally sound and accurate approach to model user attributes in social media. Extensive experiments using Twitter data have demonstrated the efficacy of our CSL approach in inferring user attributes such as account type and marital status. We also show how CSL can be used to determine important user features, and to make inference on a larger user population.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Where is the Goldmine? Finding Promising Business Locations through Facebook Data Analytics

If you were to open your own cafe, would you not want to effortlessly identify the most suitable location to set up your shop? Choosing an optimal physical location is a critical decision for numerous businesses, as many factors contribute to the final choice of the location. In this paper, we seek to address the issue by investigating the use of publicly available Facebook Pages data---which include user check-ins, types of business, and business locations---to evaluate a user-selected physical location with respect to a type of business. Using a dataset of 20,877 food businesses in Singapore, we conduct analysis of several key factors including business categories, locations, and neighboring businesses. From these factors, we extract a set of relevant features and develop a robust predictive model to estimate the popularity of a business location. Our experiments have shown that the popularity of neighboring business contributes the key features to perform accurate prediction. We finally illustrate the practical usage of our proposed approach via an interactive web application system.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Using Linear Dynamical Topic Model for Inferring Temporal Social Correlation in Latent Space

The abundance of online user data has led to a surge of interests in understanding the dynamics of social relationships using computational methods. Utilizing users' items adoption data, we develop a new method to compute the Granger-causal (GC) relationships among users. In order to handle the high dimensional and sparse nature of the adoption data, we propose to model the relationships among users in latent space instead of the original data space. We devise a Linear Dynamical Topic Model (LDTM) that can capture the dynamics of the users' items adoption behaviors in latent (topic) space. Using the time series of temporal topic distributions learned by LDTM, we conduct Granger causality tests to measure the social correlation relationships between pairs of users. We call the combination of our LDTM and Granger causality tests as Temporal Social Correlation. By conducting extensive experiments on bibliographic data, where authors are analogous to users, we show that the ordering of authors' name on their publications plays a statistically significant role in the interaction of research topics among the authors. We also present a case study to illustrate the correlational relationships between pairs of authors.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Detecting Flow Anomalies in Distributed Systems

Deep within the networks of distributed systems, one often finds anomalies that affect their efficiency and performance. These anomalies are difficult to detect because the distributed systems may not have sufficient sensors to monitor the flow of traffic within the interconnected nodes of the networks. Without early detection and making corrections, these anomalies may aggravate over time and could possibly cause disastrous outcomes in the system in the unforeseeable future. Using only coarse-grained information from the two end points of network flows, we propose a network transmission model and a localization algorithm, to detect the location of anomalies and rank them using a proposed metric within distributed systems. We evaluate our approach on passengers' records of an urbanized city's public transportation system and correlate our findings with passengers' postings on social media microblogs. Our experiments show that the metric derived using our localization algorithm gives a better ranking of anomalies as compared to standard deviation measures from statistical models. Our case studies also demonstrate that transportation events reported in social media microblogs matches the locations of our detect anomalies, suggesting that our algorithm performs well in locating the anomalies within distributed systems.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

ReputationPro: The Efficient Approaches to Contextual Transaction Trust Computation in E-Commerce Environments

In e-commerce environments, the trustworthiness of a seller is utterly important to potential buyers, especially when the seller is unknown to them. Most existing trust evaluation models compute a single value to reflect the general trust level of a seller without taking any transaction context information into account. In this paper, we first present a trust vector consisting of three values for Contextual Transaction Trust (CTT). In the computation of three CTT values, the identified three important context dimensions, including product category, transaction amount and transaction time, are taken into account. In particular, with different parameters regarding context dimensions that are specified by a buyer, different sets of CTT values can be calculated. As a result, all these values can outline the reputation profile of a seller that indicates the dynamic trust levels of a seller in different product categories, price ranges, time periods, and any necessary combination of them. We term this new model as ReputationPro. However, in ReputationPro, the computation of reputation profile requires novel algorithms for the precomputation of aggregates over large-scale ratings and transaction data of three context dimensions as well as new data structures for appropriately indexing aggregation results to promptly answer buyers' CTT requests. To solve these challenging problems, we then propose a new index scheme CMK-tree. After that, we further extend CMK-tree and propose a CMK-treeRS approach to reducing the storage space allocated to each seller. Finally, the experimental results illustrate that the CMK-tree is superior in efficiency for computing CTT values to all three existing approaches in the literature. In addition, though with reduced storage space, the CMK-treeRS approach can further improve the performance in answering buyers' CTT queries.

0 citations0 reviewsNo code linkedOpen access