ACM SIGKDD Research Articles

Integrated data-driven modeling and experimental optimization of granular hydrogel matrices

Integrated data-driven modeling and experimental optimization of granular hydrogel matrices

An Interview with Dr. Huan Liu, Winner of ACM SIGKDD 2022 Innovation Award

In recognition of outstanding technical innovations that have greatly influenced the direction of research and development in the field of knowledge discovery and data mining, Huan Liu, Ph.D. is the recipient of the 2022 ACM SIGKDD Innovation Award. Conferred annually on an individual or group, Dr. Liu was honored for his outstanding contributions to the foundation, principles and applications of social media mining and feature selection for data mining. Dr. Liu is currently professor of computer science and engineering at Arizona State University (ASU). He sat down with SIGDKDD Explorations to discuss his career, his research, and the biggest challenges facing the field.

An Interview with Dr. Charu Aggarwal, Winner of ACM SIGKDD 2022 Service Award

In recognition of outstanding professional services and contributions to the field of knowledge discovery and data mining, Charu Aggarwal, Ph.D. is the recipient of the 2022 ACM SIGKDD Service Award. Conferred annually on an individual or group, Dr. Aggarwal was honored for his years of service and many contributions that span publishing, programming, sponsorship and more in support of SIGKDD. Dr. Aggarwal is Distinguished Research Staff Member at IBM T. J. Watson Research Center and was the recipient of the 2019 SIGKDD Innovation Award. He sat down with SIGKDD Explorations to discuss how he first became involved with the KDD conference, the evolution of his volunteerism, the focus of his work at IBM, and his advice to those early in their careers.

Algorithmic fairness in computational medicine.

SummaryMachine learning models are increasingly adopted for facilitating clinical decision-making. However, recent research has shown that machine learning techniques may result in potential biases when making decisions for people in different subgroups, which can lead to detrimental effects on the health and well-being of specific demographic groups such as vulnerable ethnic minorities. This problem, termed algorithmic bias, has been extensively studied in theoretical machine learning recently. However, the impact of algorithmic bias on medicine and methods to mitigate this bias remain topics of active discussion. This paper presents a comprehensive review of algorithmic fairness in the context of computational medicine, which aims at improving medicine with computational approaches. Specifically, we overview the different types of algorithmic bias, fairness quantification metrics, and bias mitigation methods, and summarize popular software libraries and tools for bias evaluation and mitigation, with the goal of providing reference and insights to researchers and practitioners in computational medicine.

Surrogate convolutional neural network models for steady computational fluid dynamics simulations

A convolution neural network (CNN)-based approach for the construction of reduced order surrogate models for computational fluid dynamics (CFD) simulations is introduced; it is inspired by the approach of Guo, Li, and Iori [X. Guo, W. Li, and F. Iorio, Convolutional neural networks for steady flow approximation, in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '16, New York, USA, 2016, ACM, pp. 481–490]. In particular, the neural networks are trained in order to predict images of the flow field in a channel with varying obstacle based on an image of the geometry of the channel. A classical CNN with bottleneck structure and a U-Net are compared while varying the input format, the number of decoder paths, as well as the loss function used to train the networks. This approach yields very low prediction errors, in particular, when using the U-Net architecture. Furthermore, the models are also able to generalize to unseen geometries of the same type. A transfer learning approach enables the model to be trained to a new type of geometries with very low training cost. Finally, based on this transfer learning approach, a sequential learning strategy is introduced, which significantly reduces the amount of necessary training data.

An Interview with Dr. Shipeng Yu, Winner of ACM SIGKDD 2021 Service Award

Shipeng Yu, Ph.D. is the recipient of the 2021 ACM SIGKDD Service Award, which is the highest service award in the field of knowledge discovery and data mining. Conferred annually on one individual or group in recognition of outstanding professional services and contributions to the field of knowledge discovery and data mining, Dr. Yu was honored for his years of service and many accomplishments as general chair of KDD 2017 and currently as sponsorship director for SIGKDD. Dr. Yu is Director of AI Engineering, Head of the Growth AI team at LinkedIn, the world's largest professional network. He sat down with SIGKDD Explorations to discuss how he first got involved in the KDD conference in 2006, the benefits and drawbacks of virtual conferences, his work at LinkedIn, and KDD's place in the field of machine learning, data science and artificial intelligence.

A convergent algorithm for bi-orthogonal nonnegative matrix tri-factorization

A convergent algorithm for nonnegative matrix factorization (NMF) with orthogonality constraints imposed on both basis and coefficient matrices is proposed in this paper. This factorization concept was first introduced by Ding et al. (Proceedings of 12th ACM SIGKDD international conference on knowledge discovery and data mining, pp 126–135, 2006) with intent to further improve clustering capability of NMF. However, as the original algorithm was developed based on multiplicative update rules, the convergence of the algorithm cannot be guaranteed. In this paper, we utilize the technique presented in our previous work Mirzal (J Comput Appl Math 260:149–166, 2014a; Proceedings of the first international conference on advanced data and information engineering (DaEng-2013). Springer, pp 177–184, 2014b; IEEE/ACM Trans Comput Biol Bioinform 11(6):1208–1217, 2014c) to develop a convergent algorithm for this problem and prove that it converges to a stationary point inside the solution space. As it is very hard to numerically show the convergence of an NMF algorithm due to the slow convergence and numerical precision issues, experiments are instead performed to evaluate whether the algorithm has the nonincreasing property (a necessary condition for the convergence) where it is shown that the algorithm has this property. Further, clustering capability of the algorithm is also inspected by using Reuters-21578 data corpus.

Real-time prediction of upcoming respiratory events via machine learning using snoring sound signal.

The aim of the study was to inspect the acoustic properties and sleep characteristics of a preapneic snoring sound. The feasibility of forecasting upcoming respiratory events by snoring sound was also investigated. Participants with habitual snoring or a heavy breathing sound during sleep were recruited consecutively. Polysomnography was conducted, and snoring-related breathing sound was recorded simultaneously. Acoustic features and sleep features were extracted from 30-second samples, and a machine learning algorithm was used to establish 2 prediction models. A total of 74 eligible participants were included. Model 1, tested by 5-fold cross-validation, achieved an accuracy of 0.92 and an area under the curve of 0.94 for respiratory event prediction. Model 2, with acoustic features and sleep information tested by Leave-One-Out cross-validation, had an accuracy of 0.78 and an area under the curve of 0.80. Sleep position was found to be the most important among all sleep features contributing to the performance of the 2 models. Preapneic sound presented unique acoustic characteristics, and snoring-related breathing sound could be deployed as a real-time apneic event predictor. The models, combined with sleep information, serve as a promising tool for an early warning system to forecast apneic events. Wang B, Yi X, Gao J, etal. Real-time prediction of upcoming respiratory events via machine learning using snoring sound signal. J Clin Sleep Med. 2021;17(9):1777-1784.

An Interview with Dr. Michael Zeller, Winner of ACM SIGKDD 2020 Service Award

Michael Zeller, Ph.D. is the recipient of the 2020 ACM SIGKDD Service Award, which is the highest service award in the field of knowledge discovery and data mining. Conferred annually on one individual or group in recognition of outstanding professional services and contributions to the field of knowledge discovery and data mining, Dr. Zeller was honored for his years of service and many accomplishments as the secretary and treasurer for ACM SIGKDD, the organizing body of the annual KDD conference. Zeller is also head of AI strategy and solutions at Temasek, a global investment company seeking to make a difference always with tomorrow in mind. He sat down with SIGKDD Explorations to discuss how he first got involved in the KDD conference in 1999, what he learned from the first-ever virtual conference, his work at Temasek, and what excites him about the future of machine learning, data science and artificial intelligence.

An Interview with Dr. Thorsten Joachims, Winner of ACM SIGKDD 2020 Innovation Award

Thorsten Joachims, Ph.D. is the recipient of the 2020 ACM SIGKDD Innovation Award, the highest honor for technical excellence in the field of knowledge discovery and data mining. The Innovation Award is conferred annually on an individual or group of collaborators whose outstanding technical innovations have greatly influenced the direction of research and development in the field.

Trading networks and Hodge theory ∗

The problem of analyzing interconnectedness is one of today’s premier challenges in understanding systemic risk. Connections can both stabilize networks and provide pathways for contagion. The central problem in such networks is establishing global behavior from local interactions. Jiang-Lim-Yao-Ye (Jiang et al 2011 Mathematical Programming 127 1 203–244) recently introduced the use of the Hodge decomposition (see Lim 2020 SIAM Review 62 685–715 for a review), a fundamental tool from algebraic geometry, to construct global rankings from local interactions (see Barbarossa et al 2018 (2018 IEEE Data Science Workshop (DSW), IEEE) pp 51–5; Haruna and Fujiki 2016 Frontiers in Neural Circuits 10 77; Jia et al 2019 (Proc. of the XXV ACM SIGKDD International Conf. on Knowledge Discovery & Data Mining, pp 761–71 for other applications). We apply this to a study of financial networks, starting from the Eisenberg-Noe (Eisenberg and Noe 2001 Management Science 47 236–249) setup of liabilities and endowments, and construct a network of defaults. We then use Jiang-Lim-Yao-Ye to construct a global ranking from the defaults, which yields one way of quantifying ‘systemic importance’.

Inferring Protein Sequence-Function Relationships with Large-Scale Positive-Unlabeled Learning.

Machine learning can infer how protein sequence maps to function without requiring a detailed understanding of the underlying physical or biological mechanisms. It is challenging to apply existing supervised learning frameworks to large-scale experimental data generated by deep mutational scanning (DMS) and related methods. DMS data often contain high-dimensional and correlated sequence variables, experimental sampling error and bias, and the presence of missing data. Notably, most DMS data do not contain examples of negative sequences, making it challenging to directly estimate how sequence affects function. Here, we develop a positive-unlabeled (PU) learning framework to infer sequence-function relationships from large-scale DMS data. Our PU learning method displays excellent predictive performance across ten large-scale sequence-function datasets, representing proteins of different folds, functions, and library types. The estimated parameters pinpoint key residues that dictate protein structure and function. Finally, we apply our statistical sequence-function model to design highly stabilized enzymes.

Guest Editorial for Selected Papers from BIOKDD 2018 and DMBIH 2018

The papers in this special issue were presented at the 2018 17th International Workshop on Data Mining in Bioinformatics (BIOKDD), held in conjunction with the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. The Workshop was held on August 20, 2018 in London, UK.

Theory-Guided Machine Learning Finds Geometric Structure-Property Relationships for Chemisorption on Subsurface Alloys

Summary Developing physically transparent and quantitatively accurate models that relate the chemical interaction (chemisorption strength) between an adsorbate and a solid surface to the adsorption site's geometry is critical for our understanding of catalysis, corrosion, and electrochemistry. We develop a theory-guided machine-learning (ML) approach, which uses an interpretable class of ML models called generalized additive models (iGAM models), to discover predictive structure-property models that can quantify and explain the link between the geometric structure of an adsorption site and the chemisorption strength. We demonstrate the approach through several case studies, where we analyze the chemisorption strength of chemically distinct adsorbates (O, OH, S, and Cl) on subsurface metal alloy surfaces subjected to various strain- and ligand-induced changes in the local geometric structure. By comparing the ML-derived chemisorption models to previously established electronic-structure models, we clarify the critical physical parameters that control the chemisorption process on metal surfaces.

The KDD Cup 2019 Report

The KDD Cup has been a data science competition affiliated with the ACM SIGKDD conference with more than 20 years' tradition. In 2019, we organized the KDD Cup by hosting 3 parallel tracks, each with tremendous innovation. The regular machine learning (ML) track was a context-aware travel mode recommendation problem, sponsored by Baidu.com. The automatic machine learning (AutoML) track, sponsored by 4Paradigm, was about nding cost-e ective and transferable solutions for temporal relational data represented as multiple related tables. The humanity reinforcement learning (RL) track was sponsored by IBM Africa and Hexagon-ML to determine the best policy in distribution of control measures to eradicate Malaria. In 3 competitions collectively, we had more than 2,800 registered teams from over 39 countries and 230 academic and research institutions. Among the 1,200 most actively participating teams, over 5,000 individuals participated, and more than 17,000 submissions were made. A total exceeding 100 thousand U.S. dollars were awarded to the winning teams.

Data Science for Earth

At the 25th ACM SIGKDD conference on Knowledge and Data Discovery (KDD), a special Earth Day symposium was held to bring together thought leaders in academia, indus- try and government to discuss opportunities for data science to help meet the challenges facing our planet Earth. The all-day event showcased some examples of data-intensive re- search being done to study Earth-related phenomena. A key goal of the symposium was to raise awareness about the unique challenges that Earth-related datasets pose for data mining. The Earth Day website can be found at https://www. kdd.org/kdd2019/special-days/earth-day.

An Interview with Dr. Balaji Krishnapuram, Winner of SIGKDD Service Award

Dr. Balaji Krishnapuram, director and distinguished engineer at IBM Watson Health, is honored for his contributions to society through the development of machine learning products to improve healthcare. The ACM SIGKDD Service Award is the highest service award in the field of knowledge discovery and data mining. It is conferred on one individual or one group for their outstanding professional services and contributions to the field of knowledge discovery and data mining. Dr. Krishnapuram sat down with SIGKDD Explorations to discuss how he first got involved in the KDD Conference, his work at IBM Watson Health and what exites him about the future of machine learning, data science and artificial intelligence.

会議報告 The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining（KDD 2019）

会議報告 The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining（KDD 2019）

Large-margin Distribution Machine-based regression

This paper presents an efficient and robust Large-margin Distribution Machine formulation for regression. The proposed model is termed as ‘Large-margin Distribution Machine-based Regression’ (LDMR) model, and it is in the spirit of Large-margin Distribution Machine (LDM) (Zhang and Zhou, in: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, 2014) classification model. The LDM model optimizes the margin distribution instead of minimizing a single-point margin as is done in the traditional SVM. The optimization problem of the LDMR model has been mathematically derived from the optimization problem of the LDM model using an interesting result of Bi and Bennett (Neurocomputing 55(1):79–108, 2003). The resulting LDMR formulation attempts to minimize the $$\epsilon$$ -insensitive loss function and the quadratic loss function simultaneously. Further, the successive over-relaxation technique (Mangasarian and Musicant, IEEE Trans Neural Netw 10(5):1032−1037, 1999) has also been applied to speed up the training procedure of the proposed LDMR model. The experimental results on artificial datasets, UCI datasets and time-series financial datasets show that the proposed LDMR model owns better generalization ability than other existing models and is less sensitive to the presence of outliers.

Multiscale and Multimodal Analysis for Computational Biology

The papers in this special section were presented at the 16th International Workshop on Data Mining in Bioinformatics BIOKDD17. The BIOKDD17 Workshop was organized in conjunction with the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining on August 14, 2017 in Halifax, Canada. It brought together international researchers in the interacting disciplines of data mining, medical informatics, and bioinformatics at the World Trade and Convention Centre venue. The goal of this workshop is to encourage Knowledge Discovery and Data mining KDD researchers to take on the numerous challenges that bioinformatics offers. Bioinformatics is the science of managing, mining, and interpreting information from biological data. Various genome projects have contributed to an exponential growth in DNA and protein sequence databases. Rapid advances in high-throughput technologies, such as microarrays, mass spectrometry, and new/next-generation sequencing, can monitor quantitatively the presence or activity of thousands of genes, RNAs, proteins, metabolites, and compounds in a given biological state. The ongoing influx of these data, the pressing need to address complex biomedical challenges, and the gap between the two have collectively created exciting opportunities for data mining researchers.