The Data and Intelligence Systems (DAIS) Laboratory focuses on data science and artificial intelligence. The lab identifies real-world challenges and addresses them through data science and AI methodologies, leveraging evolving and unstructured data, foundation models, and human-curated knowledge to empower innovation through data-driven insights and foster intelligent systems with adaptive capabilities.

데이터 및 지능형 시스템(DAIS) 연구실은 데이터 과학 및 인공 지능에 중점을 둔다. 진화하는 비정형 데이터, 기초 모델, 인간이 큐레이팅한 지식을 활용하여 데이터 기반 통찰력을 통해 혁신을 강화하고 적응형 기능을 갖춘 지능형 시스템을 육성함으로써 실제 문제점을 해결하는 것을 목표로 한다.

Back to the Future: Look-ahead Augmentation and Parallel Self-Refinement for Time Series Forecasting

CREAM: Continual Retrieval on Dynamic Streaming Corpora with Adaptive Soft Memory

LMSC: Local Sketch Modularity Optimisation for Size-Constrained Community Search in Networks

Metadata Meets LLMs: Constructing Knowledge-Rich Citation Networks with CoT-Enhanced Representations

Sequence-aware Adaptive Graph Convolutional Recurrent Networks for Traffic Forecasting

Multi-level Diagnosis and Evaluation for Robust Tabular Feature Engineering with Large Language Models

An Analysis of City Image by Exploiting Social Media: Toward a Deeper Understanding of Multiple Characteristics and Their Temporal Changes using Machine Learning

Bi-Modal Learning for Networked Time Series

HAETAE: In-domain Table Pretraining with Header Anchoring

Mobility Networked Time-Series Forecasting Benchmark Datasets

Exploiting Representation Curvature for Boundary Detection in Time Series

Flexi-clique: Exploring Flexible and Sub-linear Clique Structures

Online Drift Detection with Maximum Concept Discrepancy

One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning

Breaking the Time-Frequency Granularity Discrepancy in Time-Series Anomaly Detection

MEGClass: Text Classification with Extremely Weak Supervision via Mutually-Enhancing Text Granularities

DynaMiTE: Discovering Explosive Topic Evolutions with User Guidance

Context Consistency Regularization for Label Sparsity in Time Series

Unsupervised Story Discovery from Continuous News Streams via Scalable Thematic Embedding

PDSum: Prototype-driven Continuous Summarization of Evolving Multi-document Sets Stream

SCStory: Self-supervised and Continual Online Story Discovery

MG-TAR: Multi-view Graph Convolutional Networks for Traffic Accident Risk Prediction

Topic Taxonomy Expansion via Hierarchy-Aware Topic Phrase Generation

Multi-view POI-level Cellular Trajectory Reconstruction for Digital Contact Tracing of Infectious Diseases

Adaptive Model Pooling for Online Deep Anomaly Detection from a Complex Evolving Data Stream

Coherence-based Label Propagation over Time Series for Accelerated Active Learning

TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters

COVID-EENet: Predicting Fine-Grained Impact of COVID-19 on Local Economies

Multiple Dynamic Outlier-Detection from a Data Stream by Exploiting Duality of Data and Queries

Ultrafast Local Outlier Detection from a Data Stream with Stationary Region Skipping

NETS: Extremely Fast Outlier Detection from a Data Stream via Set-Based Processing

MLAT: Metric Learning for kNN in Streaming Time Series

CEP-Wizard: Automatic Deployment of Distributed Complex Event Processing

Social or Financial Goals? Comparative Analysis of User Behaviors in Couchsurfing and Airbnb

Social or financial goals? Comparative analysis of user behaviors in Couchsurfing and Airbnb

MG-TAR: Multi-View Graph Convolutional Networks for Traffic Accident Risk Prediction

NETS: extremely fast outlier detection from a data stream via set-based processing

Taxocom: Topic taxonomy completion with hierarchical discovery of novel topic clusters

Breaking the time-frequency granularity discrepancy in time-series anomaly detection

Adaptive model pooling for online deep anomaly detection from a complex evolving data stream

Ultrafast local outlier detection from a data stream with stationary region skipping

Multiple dynamic outlier-detection from a data stream by exploiting duality of data and queries

Online drift detection with maximum concept discrepancy

Coherence-based label propagation over time series for accelerated active learning

Context consistency regularization for label sparsity in time series

SCStory: Self-supervised and continual online story discovery

Unsupervised story discovery from continuous news streams via scalable thematic embedding

Megclass: extremely weakly supervised text classification via mutually-enhancing text granularities

PDSum: Prototype-driven continuous summarization of evolving multi-document sets stream

One size fits all for semantic shifts: Adaptive prompt tuning for continual learning

Topic taxonomy expansion via hierarchy-aware topic phrase generation

Covid-eenet: Predicting fine-grained impact of COVID-19 on local economies

CEP-Wizard: Automatic deployment of distributed complex event processing

DynaMiTE: Discovering explosive topic evolutions with user guidance

Jae-Gil Lee

Byung Suk Lee

Hwanjun Song

Jiawei Han

Dongha Lee

Jiaming Shen

Sundong Kim

Yu Meng

Hou Pong Chan

Minseok Kim

Junghoon Kim

Xuan Wang

Susik Yoon

Uber and Airbnb, two well-known sharing economy services, are facing conflicts with traditional taxi and hotel companies because these services have monetary benefits but are free from legacy regulations. However, non-monetary-based sharing services, represented by Couchsurfing, Inc., are free from such conflict and still successful. We investigated the distinctive user participation motivation of non-monetary-based sharing services versus monetary-based ones. Specifically, a comparative analysis of Couchsurfing with Airbnb was conducted via affinity diagramming from host profiles and guest review data. The human relationship, rather than a house, is discovered as the primary shared asset and the primary satisfaction feature for Couchsurfing users. This study gives an insight to prioritize human relationships as the main design concern while developing non-monetary based sharing economy services.

Due to the continuing colossal socio-economic losses caused by traffic accidents, it is of prime importance to precisely forecast the traffic accident risk to reduce future accidents. In this paper, we use dangerous driving statistics from driving log data and multi-graph learning to enhance predictive performance. We first conduct geographical and temporal correlation analyses to quantify the relationship between dangerous driving and actual accidents. Then, to learn various dependencies between districts besides the traditional adjacency matrix, we simultaneously model both static and dynamic graphs representing the spatio-temporal contextual relationships with heterogeneous environmental data, including the dangerous driving behavior. A graph is generated for each type of the relationships. Ultimately, we propose an end-to-end framework, called MG-TAR, to effectively learn the association of multiple graphs …

This paper addresses the problem of efficiently detecting outliers from a data stream as old data points expire from and new data points enter the window incrementally. The proposed method is based on a newly discovered characteristic of a data stream that the change in the locations of data points in the data space is typically very insignificant. This observation has led to the finding that the existing distance-based outlier detection algorithms perform excessive unnecessary computations that are repetitive and/or canceling out the effects. Thus, in this paper, we propose a novel set-based approach to detecting outliers, whereby data points at similar locations are grouped and the detection of outliers or inliers is handled at the group level. Specifically, a new algorithm NETS is proposed to achieve a remarkable performance improvement by realizing set-based early identification of outliers or inliers and taking advantage of the" net effect" between expired and new data points. Additionally, NETS is capable of achieving the same efficiency even for a high-dimensional data stream through two-level dimensional filtering. Comprehensive experiments using six real-world data streams show 5 to 25 times faster processing time than state-of-the-art algorithms with comparable memory consumption. We assert that NETS opens a new possibility to real-time data stream outlier detection.

Topic taxonomies, which represent the latent topic (or category) structure of document collections, provide valuable knowledge of contents in many applications such as web search and information filtering. Recently, several unsupervised methods have been developed to automatically construct the topic taxonomy from a text corpus, but it is challenging to generate the desired taxonomy without any prior knowledge. In this paper, we study how to leverage the partial (or incomplete) information about the topic structure as guidance to find out the complete topic taxonomy. We propose a novel framework for topic taxonomy completion, named TaxoCom, which recursively expands the topic taxonomy by discovering novel sub-topic clusters of terms and documents. To effectively identify novel topics within a hierarchical topic structure, TaxoCom devises its embedding and clustering techniques to be closely-linked with …

In light of the remarkable advancements made in time-series anomaly detection(TSAD), recent emphasis has been placed on exploiting the frequency domain as well as the time domain to address the difficulties in precisely detecting pattern-wise anomalies. However, in terms of anomaly scores, the window granularity of the frequency domain is inherently distinct from the data-point granularity of the time domain. Owing to this discrepancy, the anomaly information in the frequency domain has not been utilized to its full potential for TSAD. In this paper, we propose a TSAD framework, Dual-TF, that simultaneously uses both the time and frequency domains while breaking the time-frequency granularity discrepancy. To this end, our framework employs nested-sliding windows, with the outer and inner windows responsible for the time and frequency domains, respectively, and aligns the anomaly scores of the two …

Online anomaly detection from a data stream is critical for the safety and security of many applications but is facing severe challenges due to complex and evolving data streams from IoT devices and cloud-based infrastructures. Unfortunately, existing approaches fall too short for these challenges; online anomaly detection methods bear the burden of handling the complexity while offline deep anomaly detection methods suffer from the evolving data distribution. This paper presents a framework for online deep anomaly detection, ARCUS, which can be instantiated with any autoencoder-based deep anomaly detection methods. It handles the complex and evolving data streams using an adaptive model pooling approach with two novel techniques: concept-driven inference and drift-aware model pool update; the former detects anomalies with a combination of models most appropriate for the complexity, and the latter …

Real-time outlier detection from a data stream is an increasingly important problem, especially as sensor-generated data streams abound in many applications owing to the prevalence of IoT and emergence of digital twins. Several density-based approaches have been proposed to address this problem, but arguably none of them is fast enough to meet the performance demand of real applications. This paper is founded upon a novel observation that, in many regions of the data space, data distributions hardly change across window slides. We propose a new algorithm, abbr. STARE, which identifies local regions in which data distributions hardly change and then skips updating the densities in those regions-a notion called stationary region skipping. Two techniques, data distribution approximation and cumulative net-change-based skip, are employed to efficiently and effectively implement the notion. Extensive …

Real-time outlier detection from a data stream has become increasingly important in the current hyperconnected world. This paper focuses on an important yet unaddressed challenge in continuous outlier detection: the multiplicity and dynamicity of queries. This challenge arises from various contexts of outliers evolving over time, but the state-of-the-art algorithms cannot handle the challenge effectively, as they can only process a fixed set of outlier detection queries for each data point separately. In this paper, we propose a novel algorithm, abbreviated as MDUAL, based on a new idea called duality-based unified processing. The underlying rationale is to exploit the duality of data and queries so that a group of similar data points are processed together by a group of similar queries incrementally. Two main techniques embodying the idea, data-query grouping and prioritized group processing, are employed …

Continuous learning from an immense volume of data streams becomes exceptionally critical in the internet era. However, data streams often do not conform to the same distribution over time, leading to a phenomenon called concept drift. Since a fixed static model is unreliable for inferring concept-drifted data streams, establishing an adaptive mechanism for detecting concept drift is crucial. Current methods for concept drift detection primarily assume that the labels or error rates of downstream models are given and/or underlying statistical properties exist in data streams. These approaches, however, struggle to address high-dimensional data streams with intricate irregular distribution shifts, which are more prevalent in real-world scenarios. In this paper, we propose MCD-DD, a novel concept drift detection method based on maximum concept discrepancy, inspired by the maximum mean discrepancy. Our method …

Time-series data are ubiquitous these days, but lack of the labels in time-series data is regarded as a hurdle for its broad applicability. Meanwhile, active learning has been successfully adopted to reduce the labeling efforts in various tasks. Thus, this paper addresses an important issue, time-series active learning. Inspired by the temporal coherence in time-series data, where consecutive data points tend to have the same label, our label propagation framework, called TCLP, automatically assigns a queried label to the data points within an accurately estimated time-series segment, thereby significantly boosting the impact of an individual query. Compared with traditional time-series active learning, TCLP is shown to improve the classification accuracy by up to 7.1 times when only 0.8% of data points in the entire time series are queried for their labels.

Labels are typically sparse in real-world time series due to the high annotation cost. Recently, consistency regularization techniques have been used to generate artificial labels from unlabeled augmented instances. To fully exploit the sequential characteristic of time series in consistency regularization, we propose a novel method of data augmentation called context-attached augmentation, which adds preceding and succeeding instances to a target instance to form its augmented instance. Unlike the existing augmentation techniques that modify a target instance by directly perturbing its attributes, the context-attached augmentation generates instances augmented with varying contexts while maintaining the target instance. Based on our augmentation method, we propose a context consistency regularization framework, which first adds different contexts to a target instance sampled from a given time series and then shares unitary reliability-based cross-window labels across the augmented instances to maintain consistency. We demonstrate that the proposed framework outperforms the existing state-of-the-art consistency regularization frameworks through comprehensive experiments on real-world time-series datasets.

We present a framework SCStory for online story discovery, that helps people digest rapidly published news article streams in real-time without human annotations. To organize news article streams into stories, existing approaches directly encode the articles and cluster them based on representation similarity. However, these methods yield noisy and inaccurate story discovery results because the generic article embeddings do not effectively reflect the story-indicative semantics in an article and cannot adapt to the rapidly evolving news article streams. SCStory employs self-supervised and continual learning with a novel idea of story-indicative adaptive modeling of news article streams. With a lightweight hierarchical embedding module that first learns sentence representations and then article representations, SCStory identifies story-relevant information of news articles and uses them to discover stories. The …

Unsupervised discovery of stories with correlated news articles in real-time helps people digest massive news streams without expensive human annotations. A common approach of the existing studies for unsupervised online story discovery is to represent news articles with symbolic- or graph-based embedding and incrementally cluster them into stories. Recent large language models are expected to improve the embedding further, but a straightforward adoption of the models by indiscriminately encoding all information in articles is ineffective to deal with text-rich and evolving news streams. In this work, we propose a novel thematic embedding with an off-the-shelf pretrained sentence encoder to dynamically represent articles and stories by considering their shared temporal themes. To realize the idea for unsupervised online story discovery, a scalable framework USTORY is introduced with two main techniques …

Text classification is essential for organizing unstructured text. Traditional methods rely on human annotations or, more recently, a set of class seed words for supervision, which can be costly, particularly for specialized or emerging domains. To address this, using class surface names alone as extremely weak supervision has been proposed. However, existing approaches treat different levels of text granularity (documents, sentences, or words) independently, disregarding inter-granularity class disagreements and the context identifiable exclusively through joint extraction. In order to tackle these issues, we introduce MEGClass, an extremely weakly-supervised text classification method that leverages Mutually-Enhancing Text Granularities. MEGClass utilizes coarse-and fine-grained context signals obtained by jointly considering a document’s most class-indicative words and sentences. This approach enables the learning of a contextualized document representation that captures the most discriminative class indicators. By preserving the heterogeneity of potential classes, MEGClass can select the most informative class-indicative documents as iterative feedback to enhance the initial word-based class representations and ultimately fine-tune a pre-trained text classifier. Extensive experiments on seven benchmark datasets demonstrate that MEGClass outperforms other weakly and extremely weakly supervised methods.

Summarizing text-rich documents has been long studied in the literature, but most of the existing efforts have been made to summarize a static and predefined multi-document set. With the rapid development of online platforms for generating and distributing text-rich documents, there arises an urgent need for continuously summarizing dynamically evolving multi-document sets where the composition of documents and sets is changing over time. This is especially challenging as the summarization should be not only effective in incorporating relevant, novel, and distinctive information from each concurrent multi-document set, but also efficient in serving online applications. In this work, we propose a new summarization problem, Evolving Multi-Document sets stream Summarization (EMDS), and introduce a novel unsupervised algorithm PDSum with the idea of prototype-driven continuous summarization. PDSum …

In real-world continual learning (CL) scenarios, tasks often exhibit intricate and unpredictable semantic shifts, posing challenges for fixed prompt management strategies which are tailored to only handle semantic shifts of uniform degree (i.e., uniformly mild or uniformly abrupt). To address this limitation, we propose an adaptive prompting approach that effectively accommodates semantic shifts of varying degree where mild and abrupt shifts are mixed. AdaPromptCL employs the assign-and-refine semantic grouping mechanism that dynamically manages prompt groups in accordance with the semantic similarity between tasks, enhancing the quality of grouping through continuous refinement. Our experiment results demonstrate that AdaPromptCL outperforms existing prompting methods by up to 21.3%, especially in the benchmark datasets with diverse semantic shifts between tasks.

Topic taxonomies display hierarchical topic structures of a text corpus and provide topical knowledge to enhance various NLP applications. To dynamically incorporate new topic information, several recent studies have tried to expand (or complete) a topic taxonomy by inserting emerging topics identified in a set of new documents. However, existing methods focus only on frequent terms in documents and the local topic-subtopic relations in a taxonomy, which leads to limited topic term coverage and fails to model the global taxonomy structure. In this work, we propose a novel framework for topic taxonomy expansion, named TopicExpan, which directly generates topic-related terms belonging to new topics. Specifically, TopicExpan leverages the hierarchical relation structure surrounding a new topic and the textual content of an input document for topic term generation. This approach encourages newly-inserted topics to further cover important but less frequent terms as well as to keep their relation consistency within the taxonomy. Experimental results on two real-world text corpora show that TopicExpan significantly outperforms other baseline methods in terms of the quality of output taxonomies.

Assessing the impact of the COVID-19 crisis on economies is fundamental to tailor the responses of the governments to recover from the crisis. In this paper, we present a novel approach to assessing the economic impact with a large-scale credit card transaction dataset at a fine granularity. For this purpose, we develop a fine-grained economic-epidemiological modeling framework COVID-EENet, which is featured with a two-level deep neural network. In support of the fine-grained EEM, COVID-EENet learns the impact of nearby mass infection cases on the changes of local economies in each district. Through the experiments using the nationwide dataset, given a set of active mass infection cases, COVID-EENet is shown to precisely predict the sales changes in two or four weeks for each district and business category. Therefore, policymakers can be informed of the predictive impact to put in the most effective mitigation measures. Overall, we believe that our work opens a new perspective of using financial data to recover from the economic crisis. For public use in this urgent problem, we release the source code at https://github. com/kaist-dmlab/COVID-EENet.

Complex event processing (CEP) is defined as event processing for multiple stream sources to infer events that suggest complicated circumstances. As the size of stream data becomes larger, CEP engines have been parallelized to take advantage of distributed computing. Typically, deployment of such a distributed CEP engine involves manual configuration, which has been regarded as an obstacle to its widespread adoption. In this demonstration, we present CEP-Wizard, a framework of automatically configuring and deploying a distributed CEP engine with minimum effort. The demonstration shows that even inexperienced users can easily configure and deploy it on Apache Storm with achieving high performance and low resource usage.

Dynamic topic models (DTMs) analyze text streams to capture the evolution of topics. Despite their popularity, existing DTMs are either fully supervised, requiring expensive human annotations, or fully unsupervised, producing topic evolutions that often do not cater to a user’s needs. Further, the topic evolutions produced by DTMs tend to contain generic terms that are not indicative of their designated time steps. To address these issues, we propose the task of discriminative dynamic topic discovery. This task aims to discover topic evolutions from temporal corpora that distinctly align with a set of user-provided category names and uniquely capture topics at each time step. We solve this task by developing DynaMiTE, a framework that ensembles semantic similarity, category indicative, and time indicative scores to produce informative topic evolutions. Through experiments on three diverse datasets, including the use of a newly-designed human evaluation experiment, we demonstrate that DynaMiTE is a practical and efficient framework for helping users discover high-quality topic evolutions suited to their interests.

Data & Adaptive Intelligence Systems Lab

교수님 소개

윤수식

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Back to the Future: Look-ahead Augmentation and Parallel Self-Refinement for Time Series Forecasting

CREAM: Continual Retrieval on Dynamic Streaming Corpora with Adaptive Soft Memory

LMSC: Local Sketch Modularity Optimisation for Size-Constrained Community Search in Networks

연구실 보유 특허

대학별 입시끈

우리 연구실 모집

교수님 소개

윤수식

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Back to the Future: Look-ahead Augmentation and Parallel Self-Refinement for Time Series Forecasting

CREAM: Continual Retrieval on Dynamic Streaming Corpora with Adaptive Soft Memory

LMSC: Local Sketch Modularity Optimisation for Size-Constrained Community Search in Networks

연구실 보유 특허

최근 3년간 연구실적 높은 연구실

대학별 입시끈

우리 연구실 모집