Namyong Park
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Namyong Park has a total of 79 co-authors. Here are the top co-authors by number of shared publications:
- Christos Faloutsos
Carnegie Mellon University
6 shared publications - U. Kang
Seoul National University
4 shared publications - Nesreen K. Ahmed
Intel Labs, Santa Clara, CA, USA
3 shared publications - Ryan Anthony Rossi
Adobe Research, San Jose, USA
3 shared publications - Agma Juci Machado Traina
University of São Paulo (USP)
2 shared publications - Catalina Vajiac
Carnegie Mellon University, Pittsburgh, PA, USA
2 shared publications
Latest Publications
- 9 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 12 (6) , 4863-4875
Edges Matter: An Analysis of Graph Time-Series Representations for Temporal Networks
Representations of temporal networks arising from a stream of edges lie at the heart of models learned on it and its performance on downstream applications. Previous modeling work has mainly represented a stream of timestamped edges using a time-series of graphs based on a specific time-scale $\tau$ (e.g., 1 mo). In contrast, it has recently been shown that constructing a time-series of graphs where each graph maintains a fixed $\epsilon$ number of edges, namely $\epsilon$-graph time-series, leads to better performance on downstream applications, but there has yet to be a detailed investigation on why $\epsilon$-graphs outperform $\tau$-graphs. In this work, we design extensive experiments on a benchmark of over 25 temporal network datasets, investigating the impact of edge randomization and the various representations on graph statistics. Our results indicate that the $\epsilon$-graph time-series representation effectively captures the structural properties of the graphs across time whereas the commonly used $\tau$-graph time-series mostly captures the frequency of edges. This motivates the need for a paradigm shift to developing temporal network representation learning frameworks built upon $\epsilon$-graph time-series. To help pave the way, we release a benchmark for the evaluation and development of better models.
- 9 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 12 (6) , 4863-4875
Edges Matter: An Analysis of Graph Time-Series Representations for Temporal Networks
Representations of temporal networks arising from a stream of edges lie at the heart of models learned on it and its performance on downstream applications. Previous modeling work has mainly represented a stream of timestamped edges using a time-series of graphs based on a specific time-scale $\tau$ (e.g., 1 mo). In contrast, it has recently been shown that constructing a time-series of graphs where each graph maintains a fixed $\epsilon$ number of edges, namely $\epsilon$-graph time-series, leads to better performance on downstream applications, but there has yet to be a detailed investigation on why $\epsilon$-graphs outperform $\tau$-graphs. In this work, we design extensive experiments on a benchmark of over 25 temporal network datasets, investigating the impact of edge randomization and the various representations on graph statistics. Our results indicate that the $\epsilon$-graph time-series representation effectively captures the structural properties of the graphs across time whereas the commonly used $\tau$-graph time-series mostly captures the frequency of edges. This motivates the need for a paradigm shift to developing temporal network representation learning frameworks built upon $\epsilon$-graph time-series. To help pave the way, we release a benchmark for the evaluation and development of better models.
- Open Access
- 12 April 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18 (6) , 1-23
Fairness-Aware Graph Neural Networks: A Survey
Graph Neural Networks (GNNs) have become increasingly important due to their representational power and state-of-the-art predictive performance on many fundamental learning tasks. Despite this success, GNNs suffer from fairness issues that arise as a result of the underlying graph data and the fundamental aggregation mechanism that lies at the heart of the large class of GNN models. In this article, we examine and categorize fairness techniques for improving the fairness of GNNs. We categorize these techniques by whether they focus on improving fairness in the pre-processing, in-processing (during training), or post-processing phases. We discuss how such techniques can be used together whenever appropriate and highlight the advantages and intuition as well. We also introduce an intuitive taxonomy for fairness evaluation metrics, including graph-level fairness, neighborhood-level fairness, embedding-level fairness, and prediction-level fairness metrics. In addition, graph datasets that are useful for benchmarking the fairness of GNN models are summarized succinctly. Finally, we highlight key open problems and challenges that remain to be addressed.
- 12 April 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18 (6) , 1-23
Open AccessFairness-Aware Graph Neural Networks: A Survey
Graph Neural Networks (GNNs) have become increasingly important due to their representational power and state-of-the-art predictive performance on many fundamental learning tasks. Despite this success, GNNs suffer from fairness issues that arise as a result of the underlying graph data and the fundamental aggregation mechanism that lies at the heart of the large class of GNN models. In this article, we examine and categorize fairness techniques for improving the fairness of GNNs. We categorize these techniques by whether they focus on improving fairness in the pre-processing, in-processing (during training), or post-processing phases. We discuss how such techniques can be used together whenever appropriate and highlight the advantages and intuition as well. We also introduce an intuitive taxonomy for fairness evaluation metrics, including graph-level fairness, neighborhood-level fairness, embedding-level fairness, and prediction-level fairness metrics. In addition, graph datasets that are useful for benchmarking the fairness of GNN models are summarized succinctly. Finally, we highlight key open problems and challenges that remain to be addressed.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4509-4515
CallMine: Fraud Detection and Visualization of Million-Scale Call Graphs
Given a million-scale dataset of who-calls-whom data containing imperfect labels, how can we detect existing and new fraud patterns? We propose CallMine, with carefully designed features and visualizations. Our CallMine method has the following properties: (a) Scalable, being linear on the input size, handling about 35 million records in around one hour on a stock laptop; (b) Effective, allowing natural interaction with human analysts; (c) Flexible, being applicable in both supervised and unsupervised settings; (d) Automatic, requiring no user-defined parameters. In the real world, in a multi-million-scale dataset, CallMine was able to detect fraudsters 7,000x faster, namely in a matter of hours, while expert humans took over 10 months to detect them. CIKM-ARP Categories: Application; Analytics and machine learning; Data presentation.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4509-4515
Open AccessCallMine: Fraud Detection and Visualization of Million-Scale Call Graphs
Given a million-scale dataset of who-calls-whom data containing imperfect labels, how can we detect existing and new fraud patterns? We propose CallMine, with carefully designed features and visualizations. Our CallMine method has the following properties: (a) Scalable, being linear on the input size, handling about 35 million records in around one hour on a stock laptop; (b) Effective, allowing natural interaction with human analysts; (c) Flexible, being applicable in both supervised and unsupervised settings; (d) Automatic, requiring no user-defined parameters. In the real world, in a multi-million-scale dataset, CallMine was able to detect fraudsters 7,000x faster, namely in a matter of hours, while expert humans took over 10 months to detect them. CIKM-ARP Categories: Application; Analytics and machine learning; Data presentation.
- Open Access
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (13) , 16410-16412
TgrApp: Anomaly Detection and Visualization of Large-Scale Call Graphs
Given a million-scale dataset of who-calls-whom data containing imperfect labels, how can we detect existing and new fraud patterns? We propose TgrApp, which extracts carefully designed features and provides visualizations to assist analysts in spotting fraudsters and suspicious behavior. Our TgrApp method has the following properties: (a) Scalable, as it is linear on the input size; and (b) Effective, as it allows natural interaction with human analysts, and is applicable in both supervised and unsupervised settings.
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (13) , 16410-16412
Open AccessTgrApp: Anomaly Detection and Visualization of Large-Scale Call Graphs
Given a million-scale dataset of who-calls-whom data containing imperfect labels, how can we detect existing and new fraud patterns? We propose TgrApp, which extracts carefully designed features and provides visualizations to assist analysts in spotting fraudsters and suspicious behavior. Our TgrApp method has the following properties: (a) Scalable, as it is linear on the input size; and (b) Effective, as it allows natural interaction with human analysts, and is applicable in both supervised and unsupervised settings.
- Open Access
MetaGL: Evaluation-Free Selection of Graph Learning Models via Meta-Learning
Given a graph learning task, such as link prediction, on a new graph, how can we select the best method as well as its hyperparameters (collectively called a model) without having to train or evaluate any model on the new graph? Model selection for graph learning has been largely ad hoc. A typical approach has been to apply popular methods to new datasets, but this is often suboptimal. On the other hand, systematically comparing models on the new graph quickly becomes too costly, or even impractical. In this work, we develop the first meta-learning approach for evaluation-free graph learning model selection, called MetaGL, which utilizes the prior performances of existing methods on various benchmark graph datasets to automatically select an effective model for the new graph, without any model training or evaluations. To quantify similarities across a wide variety of graphs, we introduce specialized meta-graph features that capture the structural characteristics of a graph. Then we design G-M network, which represents the relations among graphs and models, and develop a graph-based meta-learner operating on this G-M network, which estimates the relevance of each model to different graphs. Extensive experiments show that using MetaGL to select a model for the new graph greatly outperforms several existing meta-learning techniques tailored for graph learning model selection (up to 47% better), while being extremely fast at test time (~1 sec).
Open AccessMetaGL: Evaluation-Free Selection of Graph Learning Models via Meta-Learning
Given a graph learning task, such as link prediction, on a new graph, how can we select the best method as well as its hyperparameters (collectively called a model) without having to train or evaluate any model on the new graph? Model selection for graph learning has been largely ad hoc. A typical approach has been to apply popular methods to new datasets, but this is often suboptimal. On the other hand, systematically comparing models on the new graph quickly becomes too costly, or even impractical. In this work, we develop the first meta-learning approach for evaluation-free graph learning model selection, called MetaGL, which utilizes the prior performances of existing methods on various benchmark graph datasets to automatically select an effective model for the new graph, without any model training or evaluations. To quantify similarities across a wide variety of graphs, we introduce specialized meta-graph features that capture the structural characteristics of a graph. Then we design G-M network, which represents the relations among graphs and models, and develop a graph-based meta-learner operating on this G-M network, which estimates the relevance of each model to different graphs. Extensive experiments show that using MetaGL to select a model for the new graph greatly outperforms several existing meta-learning techniques tailored for graph learning model selection (up to 47% better), while being extremely fast at test time (~1 sec).
- Open Access
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 14-18
On Graph Time-Series Representations for Temporal Networks
Representations of temporal networks arising from a stream of edges lie at the heart of models learned on it and its performance on downstream applications. While previous work on dynamic modeling and embedding have focused on representing a stream of timestamped edges using a time-series of graphs based on a specific time-scale τ (e.g., 1 month), we introduce the notion of an ϵ -graph time-series that uses a fixed number of edges for each graph, and show its effectiveness in capturing fundamental structural graph statistics over time. The results indicate that the ϵ -graph time-series representation effectively captures the structural properties of the graphs across time whereas the commonly used τ -graph time-series representation captures the frequency of edges and temporal patterns with respect to their arrival in the application time. These results have many important implications especially on the design of new GNN-based models for temporal networks as well as for understanding existing models and their limitations.
- 30 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 14-18
Open AccessOn Graph Time-Series Representations for Temporal Networks
Representations of temporal networks arising from a stream of edges lie at the heart of models learned on it and its performance on downstream applications. While previous work on dynamic modeling and embedding have focused on representing a stream of timestamped edges using a time-series of graphs based on a specific time-scale τ (e.g., 1 month), we introduce the notion of an ϵ -graph time-series that uses a fixed number of edges for each graph, and show its effectiveness in capturing fundamental structural graph statistics over time. The results indicate that the ϵ -graph time-series representation effectively captures the structural properties of the graphs across time whereas the commonly used τ -graph time-series representation captures the frequency of edges and temporal patterns with respect to their arrival in the application time. These results have many important implications especially on the design of new GNN-based models for temporal networks as well as for understanding existing models and their limitations.
- Open Access
- 28 February 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 17 (2) , 1-27
DeltaShield: Information Theory for Human- Trafficking Detection
Given a million escort advertisements, how can we spot near-duplicates? Such micro-clusters of ads are usually signals of human trafficking (HT). How can we summarize them to convince law enforcement to act? Spotting micro-clusters of near-duplicate documents is useful in multiple, additional settings, including spam-bot detection in Twitter ads, plagiarism, and more. We present InfoShield , which makes the following contributions: practical , being scalable and effective on real data; parameter-free and principled , requiring no user-defined parameters; interpretable , finding a document to be the cluster representative, highlighting all the common phrases, and automatically detecting “slots” (i.e., phrases that differ in every document); and generalizable , beating or matching domain-specific methods in Twitter bot detection and HT detection, respectively, as well as being language independent. Interpretability is particularly important for the anti-HT domain, where law enforcement must visually inspect ads. Our experiments on real data show that InfoShield correctly identifies Twitter bots with an F1 score over 90% and detects HT ads with 84% precision. Moreover, it is scalable, requiring about 8 hours for 4 million documents on a stock laptop. Our incremental version, DeltaShield , allows for fast, incremental updates, with minor loss of accuracy.
- 28 February 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 17 (2) , 1-27
Open AccessDeltaShield: Information Theory for Human- Trafficking Detection
Given a million escort advertisements, how can we spot near-duplicates? Such micro-clusters of ads are usually signals of human trafficking (HT). How can we summarize them to convince law enforcement to act? Spotting micro-clusters of near-duplicate documents is useful in multiple, additional settings, including spam-bot detection in Twitter ads, plagiarism, and more. We present InfoShield , which makes the following contributions: practical , being scalable and effective on real data; parameter-free and principled , requiring no user-defined parameters; interpretable , finding a document to be the cluster representative, highlighting all the common phrases, and automatically detecting “slots” (i.e., phrases that differ in every document); and generalizable , beating or matching domain-specific methods in Twitter bot detection and HT detection, respectively, as well as being language independent. Interpretability is particularly important for the anti-HT domain, where law enforcement must visually inspect ads. Our experiments on real data show that InfoShield correctly identifies Twitter bots with an F1 score over 90% and detects HT ads with 84% precision. Moreover, it is scalable, requiring about 8 hours for 4 million documents on a stock laptop. Our incremental version, DeltaShield , allows for fast, incremental updates, with minor loss of accuracy.
- Open Access
- 17 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Knowledge-Based Dynamic Systems Modeling: A Case Study on Modeling River Water Quality
Modeling real-world phenomena is a focus of many science and engineering efforts, from ecological modeling to financial forecasting. Building an accurate model for complex and dynamic systems improves understanding of underlying processes and leads to resource efficiency. Knowledge-driven modeling builds a model based on human expertise, yet is often suboptimal. At the opposite extreme, data-driven modeling learns a model directly from data, requiring extensive data and potentially generating overfitting. We focus on an intermediate approach, model revision, in which prior knowledge and data are combined to achieve the best of both worlds. We propose a genetic model revision framework based on tree-adjoining grammar (TAG) guided genetic programming (GP), using the TAG formalism and GP operators in an effective mechanism making data-driven revisions while incorporating prior knowledge. Our framework is designed to address the high computational cost of evolutionary modeling of complex systems. Via a case study on the challenging problem of river water quality modeling, we show that the framework efficiently learns an interpretable model, with higher modeling accuracy than existing methods.
- 17 March 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessKnowledge-Based Dynamic Systems Modeling: A Case Study on Modeling River Water Quality
Modeling real-world phenomena is a focus of many science and engineering efforts, from ecological modeling to financial forecasting. Building an accurate model for complex and dynamic systems improves understanding of underlying processes and leads to resource efficiency. Knowledge-driven modeling builds a model based on human expertise, yet is often suboptimal. At the opposite extreme, data-driven modeling learns a model directly from data, requiring extensive data and potentially generating overfitting. We focus on an intermediate approach, model revision, in which prior knowledge and data are combined to achieve the best of both worlds. We propose a genetic model revision framework based on tree-adjoining grammar (TAG) guided genetic programming (GP), using the TAG formalism and GP operators in an effective mechanism making data-driven revisions while incorporating prior knowledge. Our framework is designed to address the high computational cost of evolutionary modeling of complex systems. Via a case study on the challenging problem of river water quality modeling, we show that the framework efficiently learns an interpretable model, with higher modeling accuracy than existing methods.
- Open Access
J-Recs: Principled and Scalable Recommendation Justification
Online recommendation is an essential functionality across a variety of services, including e-commerce and video streaming, where items to buy, watch, or read are suggested to users. Justifying recommendations, i.e., explaining why a user might like the recommended item, has been shown to improve user satisfaction and persuasiveness of the recommendation. In this paper, we develop a method for generating post-hoc justifications that can be applied to the output of any recommendation algorithm. Existing post-hoc methods are often limited in providing diverse justifications, as they either use only one of many available types of input data, or rely on the predefined templates. We address these limitations of earlier approaches by developing J-Recs, a method for producing concise and diverse justifications. J-Recs is a recommendation model-agnostic method that generates diverse justifications based on various types of product and user data (e.g., purchase history and product attributes). The challenge of jointly processing multiple types of data is addressed by designing a principled graph-based approach for justification generation. In addition to theoretical analysis, we present an extensive evaluation on synthetic and real-world data. Our results show that J-Recs satisfies desirable properties of justifications, and efficiently produces effective justifications, matching user preferences up to 20% more accurately than baselines.
Open AccessJ-Recs: Principled and Scalable Recommendation Justification
Online recommendation is an essential functionality across a variety of services, including e-commerce and video streaming, where items to buy, watch, or read are suggested to users. Justifying recommendations, i.e., explaining why a user might like the recommended item, has been shown to improve user satisfaction and persuasiveness of the recommendation. In this paper, we develop a method for generating post-hoc justifications that can be applied to the output of any recommendation algorithm. Existing post-hoc methods are often limited in providing diverse justifications, as they either use only one of many available types of input data, or rely on the predefined templates. We address these limitations of earlier approaches by developing J-Recs, a method for producing concise and diverse justifications. J-Recs is a recommendation model-agnostic method that generates diverse justifications based on various types of product and user data (e.g., purchase history and product attributes). The challenge of jointly processing multiple types of data is addressed by designing a principled graph-based approach for justification generation. In addition to theoretical analysis, we present an extensive evaluation on synthetic and real-world data. Our results show that J-Recs satisfies desirable properties of justifications, and efficiently produces effective justifications, matching user preferences up to 20% more accurately than baselines.
- Open Access
- 20 August 2020
- Published by Association for Computing Machinery (ACM)
- p. 503-512
MultiImport: Inferring Node Importance in a Knowledge Graph from Multiple Input Signals
Given multiple input signals, how can we infer node importance in a knowledge graph (KG)? Node importance estimation is a crucial and challenging task that can benefit a lot of applications including recommendation, search, and query disambiguation. A key challenge towards this goal is how to effectively use input from different sources. On the one hand, a KG is a rich source of information, with multiple types of nodes and edges. On the other hand, there are external input signals, such as the number of votes or pageviews, which can directly tell us about the importance of entities in a KG. While several methods have been developed to tackle this problem, their use of these external signals has been limited as they are not designed to consider multiple signals simultaneously. In this paper, we develop an end-to-end model MultiImport, which infers latent node importance from multiple, potentially overlapping, input signals. MultiImport is a latent variable model that captures the relation between node importance and input signals, and effectively learns from multiple signals with potential conflicts. Also, MultiImport provides an effective estimator based on attentive graph neural networks. We ran experiments on real-world KGs to show that MultiImport handles several challenges involved with inferring node importance from multiple input signals, and consistently outperforms existing methods, achieving up to 23.7% higher [email protected] than the state-of-the-art method.
- 20 August 2020
- Published by Association for Computing Machinery (ACM)
- p. 503-512
Open AccessMultiImport: Inferring Node Importance in a Knowledge Graph from Multiple Input Signals
Given multiple input signals, how can we infer node importance in a knowledge graph (KG)? Node importance estimation is a crucial and challenging task that can benefit a lot of applications including recommendation, search, and query disambiguation. A key challenge towards this goal is how to effectively use input from different sources. On the one hand, a KG is a rich source of information, with multiple types of nodes and edges. On the other hand, there are external input signals, such as the number of votes or pageviews, which can directly tell us about the importance of entities in a KG. While several methods have been developed to tackle this problem, their use of these external signals has been limited as they are not designed to consider multiple signals simultaneously. In this paper, we develop an end-to-end model MultiImport, which infers latent node importance from multiple, potentially overlapping, input signals. MultiImport is a latent variable model that captures the relation between node importance and input signals, and effectively learns from multiple signals with potential conflicts. Also, MultiImport provides an effective estimator based on attentive graph neural networks. We ran experiments on real-world KGs to show that MultiImport handles several challenges involved with inferring node importance from multiple input signals, and consistently outperforms existing methods, achieving up to 23.7% higher [email protected] than the state-of-the-art method.