A Phylogeny-based Test of Mediation Effect in Microbiome

Recent studies suggest that the microbiome can be an important mediator in the effect of a treatment on an outcome. Microbiome data generated from sequencing experiments contain the relative abundance of a large number of microbial taxa with their evolutionary relationships represented by a phylogenetic tree. The compositional and high-dimensional nature of the microbiome mediator invalidates standard mediation analyses. We propose a phylogeny-based mediation analysis method (PhyloMed) for the microbiome mediator. PhyloMed models the microbiome mediation effect through a cascade of independent local mediation models on the internal nodes of the phylogenetic tree. Each local model captures the mediation effect of a subcomposition at a given taxonomic resolution. The method improves the power of the mediation test by enriching weak and sparse signals across mediating taxa that tend to cluster on the tree. In each local model, we further empower PhyloMed by using a mixture distribution to obtain the subcomposition mediation test p-value, which takes into account the composite nature of the null hypothesis. PhyloMed enables us to test the overall mediation effect of the entire microbial community and pinpoint internal nodes with significant subcomposition mediation effects. Our extensive simulations demonstrate the validity of PhyloMed and its substantial power gain over existing methods. An application to a real study further showcases the advantages of our method.

Data Augmentation for Graph Convolutional Network on Semi-Supervised Classification

Data augmentation aims to generate new and synthetic features from the original data, which can identify a better representation of data and improve the performance and generalizability of downstream tasks. However, data augmentation for graph-based models remains a challenging problem, as graph data is more complex than traditional data, which consists of two features with different properties: graph topology and node attributes. In this paper, we study the problem of graph data augmentation for Graph Convolutional Network (GCN) in the context of improving the node embeddings for semi-supervised node classification. Specifically, we conduct cosine similarity based cross operation on the original features to create new graph features, including new node attributes and new graph topologies, and we combine them as new pairwise inputs for specific GCNs. Then, we propose an attentional integrating model to weighted sum the hidden node embeddings encoded by these GCNs into the final node embeddings. We also conduct a disparity constraint on these hidden node embeddings when training to ensure that non-redundant information is captured from different features. Experimental results on five real-world datasets show that our method improves the classification accuracy with a clear margin (+2.5% - +84.2%) than the original GCN model.

On maximizing a monotone $k$-submodular function under a knapsack constraint

We study the problem of maximizing a monotone $k$-submodular function $f$ under a knapsack constraint, where a $k$-submodular function is a natural generalization of a submodular function to $k$ dimensions. We present a deterministic $(frac12-frac{1}{2e})$-approximation algorithm that evaluates $f$ $O(n^5k^4)$ times.

Mechanism Design for Facility Location Games with Candidate Locations

We study the facility location games with candidate locations from a mechanism design perspective. Suppose there are n agents located in a metric space whose locations are their private information, and a group of candidate locations for building facilities. The authority plans to build some homogeneous facilities among these candidates to serve the agents, who bears a cost equal to the distance to the closest facility. The goal is to design mechanisms for minimizing the total/maximum cost among the agents. For the single-facility problem under the maximum-cost objective, we give a deterministic 3-approximation group strategy-proof mechanism, and prove that no deterministic (or randomized) strategy-proof mechanism can have an approximation ratio better than 3 (or 2). For the two-facility problem on a line, we give an anonymous deterministic group strategy-proof mechanism that is (2n-3)-approximation for the total-cost objective, and 3-approximation for the maximum-cost objective. We also provide (asymptotically) tight lower bounds on the approximation ratio.

Price of Fairness in Budget Division for Egalitarian Social Welfare

We study a participatory budgeting problem of aggregating the preferences of agents and dividing a budget over the projects. A budget division solution is a probability distribution over the projects. The main purpose of our study concerns the comparison between the system optimum solution and a fair solution. We are interested in assessing the quality of fair solutions, i.e., in measuring the system efficiency loss under a fair allocation compared to the one that maximizes (egalitarian) social welfare. This indicator is called the price of fairness. We are also interested in the performance of several aggregation rules. Asymptotically tight bounds are provided both for the price of fairness and the efficiency guarantee of aggregation rules.

PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data

In comparison with person re-identification (ReID), which has been widely studied in the research community, vehicle ReID has received less attention. Vehicle ReID is challenging due to 1) high intra-class variability (caused by the dependency of shape and appearance on viewpoint), and 2) small inter-class variability (caused by the similarity in shape and appearance between vehicles produced by different manufacturers). To address these challenges, we propose a Pose-Aware Multi-Task Re-Identification (PAMTRI) framework. This approach includes two innovations compared with previous methods. First, it overcomes viewpoint-dependency by explicitly reasoning about vehicle pose and shape via keypoints, heatmaps and segments from pose estimation. Second, it jointly classifies semantic vehicle attributes (colors and types) while performing ReID, through multi-task learning with the embedded pose representations. Since manually labeling images with detailed pose and attribute information is prohibitive, we create a large-scale highly randomized synthetic dataset with automatically annotated vehicle attributes for training. Extensive experiments validate the effectiveness of each proposed component, showing that PAMTRI achieves significant improvement over state-of-the-art on two mainstream vehicle ReID benchmarks: VeRi and CityFlow-ReID. Code and models are available at https://github.com/NVlabs/PAMTRI.

CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification

Urban traffic optimization using traffic cameras as sensors is driving the need to advance state-of-the-art multi-target multi-camera (MTMC) tracking. This work introduces CityFlow, a city-scale traffic camera dataset consisting of more than 3 hours of synchronized HD videos from 40 cameras across 10 intersections, with the longest distance between two simultaneous cameras being 2.5 km. To the best of our knowledge, CityFlow is the largest-scale dataset in terms of spatial coverage and the number of cameras/videos in an urban environment. The dataset contains more than 200K annotated bounding boxes covering a wide range of scenes, viewing angles, vehicle models, and urban traffic flow conditions. Camera geometry and calibration information are provided to aid spatio-temporal analysis. In addition, a subset of the benchmark is made available for the task of image-based vehicle re-identification (ReID). We conducted an extensive experimental evaluation of baselines/state-of-the-art approaches in MTMC tracking, multi-target single-camera (MTSC) tracking, object detection, and image-based ReID on this dataset, analyzing the impact of different network architectures, loss functions, spatio-temporal models and their combinations on task effectiveness. An evaluation server is launched with the release of our benchmark at the 2019 AI City Challenge (https://www.aicitychallenge.org/) that allows researchers to compare the performance of their newest techniques. We expect this dataset to catalyze research in this field, propel the state-of-the-art forward, and lead to deployed traffic optimization(s) in the real world.

MOANA: An Online Learned Adaptive Appearance Model for Robust Multiple Object Tracking in 3D

Multiple object tracking has been a challenging field, mainly due to noisy detection sets and identity switch caused by occlusion and similar appearance among nearby targets. Previous works rely on appearance models built on individual or several selected frames for the comparison of features, but they cannot encode long-term appearance changes caused by pose, viewing angle and lighting conditions. In this work, we propose an adaptive model that learns online a relatively long-term appearance change of each target. The proposed model is compatible with any feature of fixed dimension or their combination, whose learning rates are dynamically controlled by adaptive update and spatial weighting schemes. To handle occlusion and nearby objects sharing similar appearance, we also design cross-matching and re-identification schemes based on the application of the proposed adaptive appearance models. Additionally, the 3D geometry information is effectively incorporated in our formulation for data association. The proposed method outperforms all the state-of-the-art on the MOTChallenge 3D benchmark and achieves real-time computation with only a standard desktop CPU. It has also shown superior performance over the state-of-the-art on the 2D benchmark of MOTChallenge.

Multiple-Kernel Based Vehicle Tracking Using 3D Deformable Model and Camera Self-Calibration

Tracking of multiple objects is an important application in AI City geared towards solving salient problems related to safety and congestion in an urban environment. Frequent occlusion in traffic surveillance has been a major problem in this research field. In this challenge, we propose a model-based vehicle localization method, which builds a kernel at each patch of the 3D deformable vehicle model and associates them with constraints in 3D space. The proposed method utilizes shape fitness evaluation besides color information to track vehicle objects robustly and efficiently. To build 3D car models in a fully unsupervised manner, we also implement evolutionary camera self-calibration from tracking of walking humans to automatically compute camera parameters. Additionally, the segmented foreground masks which are crucial to 3D modeling and camera self-calibration are adaptively refined by multiple-kernel feedback from tracking. For object detection/classification, the state-of-the-art single shot multibox detector (SSD) is adopted to train and test on the NVIDIA AI City Dataset. To improve the accuracy on categories with only few objects, like bus, bicycle and motorcycle, we also employ the pretrained model from YOLO9000 with multi-scale testing. We combine the results from SSD and YOLO9000 based on ensemble learning. Experiments show that our proposed tracking system outperforms both state-of-the-art of tracking by segmentation and tracking by detection.