Slobodan Vucetic

IJCAI Conference 2025 Conference Paper

Deep Learning-Based Pedestrian Simulation with Limited Real-World Training Data: An Evaluation Framework

• Vahid Mahzoon
• Abigail Liu
• Slobodan Vucetic

Simulating pedestrian movement is important for applications such as disaster management, robotics, and game design. While deep learning models have been extensively used on related problems, their use as pedestrian simulators remains relatively unexplored. This paper aims to encourage more research in this direction in two ways. First, it proposes an evaluation framework that is applicable to both traditional and deep learning based simulators. Second, it proposes and evaluates several ideas related to input representation, choice of neural architecture, exploiting knowledge-based simulators in data poor regimes, and repurposing trajectory prediction models. Our extensive experiments provide several useful insights for future research in pedestrian simulation. The code is available at https: //github. com/vmahzoon76/DL-Crowd-Sim.

ECAI Conference 2023 Conference Paper

Group Activity Recognition in Basketball Tracking Data - Neural Embeddings in Team Sports (NETS)

• Sandro Hauri
• Slobodan Vucetic

Like many team sports, basketball involves two groups of players who engage in collaborative and adversarial activities to win a game. Players and teams are executing various complex strategies to gain an advantage over their opponents. Defining, identifying, and analyzing different types of activities is an important task in sports analytics, as it can lead to better strategies and decisions by the players and coaching staff. The objective of this paper is to automatically recognize basketball group activities from tracking data representing locations of players and the ball during a game. We propose a novel deep learning approach for group activity recognition (GAR) in team sports called NETS. To efficiently model the player relations in team sports, we combined a Transformer-based architecture with LSTM embedding, and a team-wise pooling layer to recognize the group activity. Training such a neural network generally requires a large amount of annotated data, which incurs high labeling cost. To alleviate this problem, we pretrain the neural network on a self-supervised trajectory prediction task and fine-tune it using a mix of strong and weak labels. We used a large tracking data set from 632 NBA games to evaluate our approach. The results show that NETS is capable of learning group activities with high accuracy, and that self- and weak-supervised training in NETS have a positive impact on GAR accuracy.

IJCAI Conference 2021 Conference Paper

Sample Efficient Decentralized Stochastic Frank-Wolfe Methods for Continuous DR-Submodular Maximization

• Hongchang Gao
• Hanzi Xu
• Slobodan Vucetic

Continuous DR-submodular maximization is an important machine learning problem, which covers numerous popular applications. With the emergence of large-scale distributed data, developing efficient algorithms for the continuous DR-submodular maximization, such as the decentralized Frank-Wolfe method, became an important challenge. However, existing decentralized Frank-Wolfe methods for this kind of problem have the sample complexity of $\mathcal{O}(1/\epsilon^3)$, incurring a large computational overhead. In this paper, we propose two novel sample efficient decentralized Frank-Wolfe methods to address this challenge. Our theoretical results demonstrate that the sample complexity of the two proposed methods is $\mathcal{O}(1/\epsilon^2)$, which is better than $\mathcal{O}(1/\epsilon^3)$ of the existing methods. As far as we know, this is the first published result achieving such a favorable sample complexity. Extensive experimental results confirm the effectiveness of the proposed methods.

ICML Conference 2020 Conference Paper

Growing Adaptive Multi-hyperplane Machines

• Nemanja Djuric
• Zhuang Wang
• Slobodan Vucetic

Adaptive Multi-hyperplane Machine (AMM) is an online algorithm for learning Multi-hyperplane Machine (MM), a classification model which allows multiple hyperplanes per class. AMM is based on Stochastic Gradient Descent (SGD), with training time comparable to linear Support Vector Machine (SVM) and significantly higher accuracy. On the other hand, empirical results indicate there is a large accuracy gap between AMM and non-linear SVMs. In this paper we show that this performance gap is not due to limited representability of the MM model, as it can represent arbitrary concepts. We set to explain the connection between the AMM and Learning Vector Quantization (LVQ) algorithms, and introduce a novel Growing AMM (GAMM) classifier motivated by Growing LVQ, that imputes duplicate hyperplanes into the MM model during SGD training. We provide theoretical results showing that GAMM has favorable convergence properties, and analyze the generalization bound of the MM models. Experiments indicate that GAMM achieves significantly improved accuracy on non-linear problems, with only slightly slower training compared to AMM. On some tasks GAMM comes close to non-linear SVM, and outperforms other popular classifiers such as Neural Networks and Random Forests.

IJCAI Conference 2019 Conference Paper

Medical Concept Representation Learning from Multi-source Data

• Tian Bai
• Brian L. Egleston
• Richard Bleicher
• Slobodan Vucetic

Representing words as low dimensional vectors is very useful in many natural language processing tasks. This idea has been extended to medical domain where medical codes listed in medical claims are represented as vectors to facilitate exploratory analysis and predictive modeling. However, depending on a type of a medical provider, medical claims can use medical codes from different ontologies or from a combination of ontologies, which complicates learning of the representations. To be able to properly utilize such multi-source medical claim data, we propose an approach that represents medical codes from different ontologies in the same vector space. We first modify the Pointwise Mutual Information (PMI) measure of similarity between the codes. We then develop a new negative sampling method for word2vec model that implicitly factorizes the modified PMI matrix. The new approach was evaluated on the code cross-reference problem, which aims at identifying similar codes across different ontologies. In our experiments, we evaluated cross-referencing between ICD-9 and CPT medical code ontologies. Our results indicate that vector representations of codes learned by the proposed approach provide superior cross-referencing when compared to several existing approaches.

AIJ Journal 2016 Journal Article

Semi-supervised combination of experts for aerosol optical depth estimation

• Nemanja Djuric
• Lakesh Kansakar
• Slobodan Vucetic

Aerosols are small airborne particles produced by natural and man-made sources. Aerosol Optical Depth (AOD), recognized as one of the most important quantities in understanding and predicting the Earth's climate, is estimated daily on a global scale by several Earth-observing satellite instruments. Each instrument has different coverage and sensitivity to atmospheric and surface conditions, and, as a result, the quality of AOD estimated by different instruments varies across the globe. We present a semi-supervised method for learning how to aggregate estimations from multiple satellite instruments into a more accurate estimate, where labels come from a small number of accurate and expensive ground-based instruments. The method also accounts for the problem of missing experts, an issue inherent to the AOD estimation task. By assuming a context-dependent prior, the model is capable of incorporating additional information and providing estimates even when there are no available experts. Moreover, the proposed method uses a latent variable to partition the data, so that in each partition the expert AOD estimations are aggregated in a different, optimal way. We applied the method to combine global AOD estimations from 5 instruments aboard 4 satellites, and the results indicate it can successfully exploit labeled and unlabeled data to produce accurate aggregated AOD estimations.

AAAI Conference 2014 Conference Paper

Non-Linear Label Ranking for Large-Scale Prediction of Long-Term User Interests

• Nemanja Djuric
• Mihajlo Grbovic
• Vladan Radosavljevic
• Narayan Bhamidipati
• Slobodan Vucetic

We consider the problem of personalization of online services from the viewpoint of ad targeting, where we seek to find the best ad categories to be shown to each user, resulting in improved user experience and increased advertisers’ revenue. We propose to address this problem as a task of ranking the ad categories depending on a user’s preference, and introduce a novel label ranking approach capable of efficiently learning non-linear, highly accurate models in large-scale settings. Experiments on a real-world advertising data set with more than 3. 2 million users show that the proposed algorithm outperforms the existing solutions in terms of both rank loss and top-K retrieval performance, strongly suggesting the benefit of using the proposed model on large-scale ranking problems.

AAAI Conference 2014 Conference Paper

Spatial Scan for Disease Mapping on a Mobile Population

• Liang Lan
• Vuk Malbasa
• Slobodan Vucetic

In disease mapping, the spatial scan statistic is used to detect spatial regions where population is exposed to a significantly higher disease risk than expected. In this important application, the current residence is typically used to define the location of individuals from the population. Considering the mobility of humans at various temporal and spatial scales, using only information about the current residence may be an insufficiently informative proxy because it ignores a multitude of exposures that may occur away from home, or which had occurred at previous residences. In this paper, we propose a spatial scan statistic that is appropriate for disease mapping on mobile populations. We formulate a computationally efficient algorithm that uses the proposed statistic to find significant high-risk regions from mobile population’s disease status data. The algorithm is applicable on large populations and over dense spatial grids. The experimental results demonstrate that the proposed algorithm is computationally efficient and outperforms the traditional disease clustering approaches at discovering high-risk regions in mobile populations.

JMLR Journal 2013 Journal Article

BudgetedSVM: A Toolbox for Scalable SVM Approximations

• Nemanja Djuric
• Liang Lan
• Slobodan Vucetic
• Zhuang Wang

We present BudgetedSVM, an open-source C++ toolbox comprising highly-optimized implementations of recently proposed algorithms for scalable training of Support Vector Machine (SVM) approximators: Adaptive Multi-hyperplane Machines, Low-rank Linearization SVM, and Budgeted Stochastic Gradient Descent. BudgetedSVM trains models with accuracy comparable to LibSVM in time comparable to LibLinear, solving non-linear problems with millions of high-dimensional examples within minutes on a regular computer. We provide command-line and Matlab interfaces to BudgetedSVM, an efficient API for handling large-scale, high- dimensional data sets, as well as detailed documentation to help developers use and further extend the toolbox. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2013. ( edit, beta )

AAAI Conference 2013 Conference Paper

Continuous Conditional Random Fields for Efficient Regression in Large Fully Connected Graphs

• Kosta Ristovski
• Vladan Radosavljevic
• Slobodan Vucetic
• Zoran Obradovic

When used for structured regression, powerful Conditional Random Fields (CRFs) are typically restricted to modeling effects of interactions among examples in local neighborhoods. Using more expressive representation would result in dense graphs, making these methods impractical for large-scale applications. To address this issue, we propose an effective CRF model with linear scale-up properties regarding approximate learning and inference for structured regression on large, fully connected graphs. The proposed method is validated on real-world large-scale problems of image denoising and remote sensing. In conducted experiments, we demonstrated that dense connectivity provides an improvement in prediction accuracy. Inference time of less than ten seconds on graphs with millions of nodes and trillions of edges makes the proposed model an attractive tool for large-scale, structured regression problems.

IJCAI Conference 2013 Conference Paper

Multi-Prototype Label Ranking with Novel Pairwise-to-Total-Rank Aggregation

• Mihajlo Grbovic
• Nemanja Djuric
• Slobodan Vucetic

We propose a multi-prototype-based algorithm for online learning of soft pairwise-preferences over labels. The algorithm learns soft label preferences via minimization of the proposed soft rank-loss measure, and can learn from total orders as well as from various types of partial orders. The soft pairwise preference algorithm outputs are further aggregated to produce a total label ranking prediction using a novel aggregation algorithm that outperforms existing aggregation solutions. Experiments on synthetic and real-world data demonstrate stateof-the-art performance of the proposed model.

IJCAI Conference 2013 Conference Paper

Semi-Supervised Learning for Integration of Aerosol Predictions from Multiple Satellite Instruments

• Nemanja Djuric
• Lakesh Kansakar
• Slobodan Vucetic

Aerosol Optical Depth (AOD), recognized as one of the most important quantities in understanding and predicting the Earth’s climate, is estimated daily on a global scale by several Earth-observing satellite instruments. Each instrument has different coverage and sensitivity to atmospheric and surface conditions, and, as a result, the quality of AOD estimated by different instruments varies across the globe. We present a method for learning how to aggregate AOD estimations from multiple satellite instruments into a more accurate estimation. The proposed method is semi-supervised, as it is able to learn from a small number of labeled data, where labels come from a few accurate and expensive ground-based instruments, and a large number of unlabeled data. The method uses a latent variable to partition the data, so that in each partition the expert AOD estimations are aggregated in a different, optimal way. We applied the method to combine AOD estimations from 5 instruments aboard 4 satellites, and the results indicate that it can successfully exploit labeled and unlabeled data to produce accurate aggregated AOD estimations.

JMLR Journal 2012 Journal Article

Breaking the Curse of Kernelization: Budgeted Stochastic Gradient Descent for Large-Scale SVM Training

• Zhuang Wang
• Koby Crammer
• Slobodan Vucetic

Online algorithms that process one example at a time are advantageous when dealing with very large data or with data streams. Stochastic Gradient Descent (SGD) is such an algorithm and it is an attractive choice for online Support Vector Machine (SVM) training due to its simplicity and effectiveness. When equipped with kernel functions, similarly to other SVM learning algorithms, SGD is susceptible to the curse of kernelization that causes unbounded linear growth in model size and update time with data size. This may render SGD inapplicable to large data sets. We address this issue by presenting a class of Budgeted SGD (BSGD) algorithms for large-scale kernel SVM training which have constant space and constant time complexity per update. Specifically, BSGD keeps the number of support vectors bounded during training through several budget maintenance strategies. We treat the budget maintenance as a source of the gradient error, and show that the gap between the BSGD and the optimal SVM solutions depends on the model degradation due to budget maintenance. To minimize the gap, we study greedy budget maintenance methods based on removal, projection, and merging of support vectors. We propose budgeted versions of several popular online SVM algorithms that belong to the SGD family. We further derive BSGD algorithms for multi-class SVM training. Comprehensive empirical results show that BSGD achieves higher accuracy than the state-of-the-art budgeted online algorithms and comparable to non-budget algorithms, while achieving impressive computational efficiency both in time and space during training and prediction. [abs] [ pdf ][ bib ] &copy JMLR 2012. ( edit, beta )

AAAI Conference 2012 Conference Paper

Convex Kernelized Sorting

• Nemanja Djuric
• Mihajlo Grbovic
• Slobodan Vucetic

Kernelized sorting is a method for aligning objects across two domains by considering within-domain similarity, without a need to specify a cross-domain similarity measure. In this paper we present the Convex Kernelized Sorting method where, unlike in the previous approaches, the cross-domain object matching is formulated as a convex optimization problem, leading to simpler optimization and global optimum solution. Our method outputs soft alignments between objects, which can be used to rank the best matches for each object, or to visualize the object matching and verify the correct choice of the kernel. It also allows for computing hard one-to-one alignments by solving the resulting Linear Assignment Problem. Experiments on a number of cross-domain matching tasks show the strength of the proposed method, which consistently achieves higher accuracy than the existing methods.

AAAI Conference 2012 Conference Paper

Sparse Principal Component Analysis with Constraints

• Mihajlo Grbovic
• Christopher Dance
• Slobodan Vucetic

The sparse principal component analysis is a variant of the classical principal component analysis, which finds linear combinations of a small number of features that maximize variance across data. In this paper we propose a methodology for adding two general types of feature grouping constraints into the original sparse PCA optimization procedure. We derive convex relaxations of the considered constraints, ensuring the convexity of the resulting optimization problem. Empirical evaluation on three real-world problems, one in process monitoring sensor networks and two in social networks, serves to illustrate the usefulness of the proposed methodology.

ECAI Conference 2010 Conference Paper

Continuous Conditional Random Fields for Regression in Remote Sensing

• Vladan Radosavljevic
• Slobodan Vucetic
• Zoran Obradovic

Conditional random fields (CRF) are widely used for predicting output variables that have some internal structure. Most of the CRF research has been done on structured classification where the outputs are discrete. In this study we propose a CRF probabilistic model for structured regression that uses multiple non-structured predictors as its features. We construct features as squared prediction errors and show that this results in a Gaussian predictor. Learning becomes a convex optimization problem leading to a global solution for a set of parameters. Inference can be conveniently conducted through matrix computation. Experimental results on the remote sensing problem of estimating Aerosol Optical Depth (AOD) provide strong evidence that the proposed CRF model successfully exploits the inherent spatio-temporal properties of AOD data. The experiments revealed that CRF are more accurate than the baseline neural network and domain-based predictors.

ICML Conference 2010 Conference Paper

Multi-Class Pegasos on a Budget

• Zhuang Wang
• Koby Crammer
• Slobodan Vucetic

EAAI Journal 2006 Journal Article

A statistical complement to deterministic algorithms for the retrieval of aerosol optical thickness from radiance data

• Bo Han
• Slobodan Vucetic
• Amy Braverman
• Zoran Obradovic

As a complement to the conventional deterministic geophysical algorithms, we consider a faster, but less accurate approach: training regression models to predict aerosol optical thickness (AOT) from radiance data. In our study, neural networks trained on a global data set are employed as a global retrieval method. Inverse distance spatial interpolation and region-specific neural networks trained on restricted, localized areas provide local models. We then develop two integrated statistical methods: local error correction of global retrievals and an optimal weighted average of global and local components. The algorithms are evaluated on the problem of deriving AOT from raw radiances observed by the Multi-angle Imaging SpectroRadiometer (MISR) instrument onboard NASA's Terra satellite. Integrated statistical approaches were clearly superior to global and local models alone. The best compromise between speed and accuracy was obtained through the weighted averaging of global neural networks and spatial interpolation. The results show that, while much faster, statistical retrievals can be quite comparable in accuracy to the far more computationally demanding deterministic methods. Differences in quality vary with season and model complexity.

ECAI Conference 2004 Conference Paper

Towards Efficient Learning of Neural Network Ensembles from Arbitrarily Large Datasets

• Kang Peng
• Zoran Obradovic
• Slobodan Vucetic

ICML Conference 2000 Conference Paper

Discovering Homogeneous Regions in Spatial Data through Competition

• Slobodan Vucetic
• Zoran Obradovic