Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection

As an inherently ill-posed problem, depth estimation from single images is the most challenging part of monocular 3D object detection (M3OD). Many existing methods rely on preconceived assumptions to bridge the missing spatial information in monocular images, and predict a sole depth value for every object of interest. However, these assumptions do not always hold in practical applications. To tackle this problem, we propose a depth solving system that fully explores the visual clues from the subtasks in M3OD and generates multiple estimations for the depth of each target. Since the depth estimations rely on different assumptions in essence, they present diverse distributions. Even if some assumptions collapse, the estimations established on the remaining assumptions are still reliable. In addition, we develop a depth selection and combination strategy. This strategy is able to remove abnormal estimations caused by collapsed assumptions, and adaptively combine the remaining estimations into a single one. In this way, our depth solving system becomes more precise and robust. Exploiting the clues from multiple subtasks of M3OD and without introducing any extra information, our method surpasses the current best method by more than 20% relatively on the Moderate level of test split in the KITTI 3D object detection benchmark, while still maintaining real-time efficiency.

AWAPart: Adaptive Workload-Aware Partitioning of Knowledge Graphs

Large-scale knowledge graphs are increasingly common in many domains. Their large sizes often exceed the limits of systems storing the graphs in a centralized data store, especially if placed in main memory. To overcome this, large knowledge graphs need to be partitioned into multiple sub-graphs and placed in nodes in a distributed system. But querying these fragmented sub-graphs poses new challenges, such as increased communication costs, due to distributed joins involving cut edges. To combat these problems, a good partitioning should reduce the edge cuts while considering a given query workload. However, a partitioned graph needs to be continually re-partitioned to accommodate changes in the query workload and maintain a good average processing time. In this paper, an adaptive partitioning method for large-scale knowledge graphs is introduced, which adapts the partitioning in response to changes in the query workload. Our evaluation demonstrates that the performance of processing time for queries is improved after dynamically adapting the partitioning of knowledge graph triples.

On the Performance of Machine Learning Methods for Breakthrough Curve Prediction

Reactive flows are important part of numerous technical and environmental processes. Often monitoring the flow and species concentrations within the domain is not possible or is expensive, in contrast, outlet concentration is straightforward to measure. In connection with reactive flows in porous media, the term breakthrough curve is used to denote the time dependency of the outlet concentration with prescribed conditions at the inlet. In this work we apply several machine learning methods to predict breakthrough curves from the given set of parameters. In our case the parameters are the Damk\"ohler and Peclet numbers. We perform a thorough analysis for the one-dimensional case and also provide the results for the three-dimensional case.

Uncertainty Quantification for Transport in Porous media using Parameterized Physics Informed neural Networks

We present a Parametrization of the Physics Informed Neural Network (P-PINN) approach to tackle the problem of uncertainty quantification in reservoir engineering problems. We demonstrate the approach with the immiscible two phase flow displacement (Buckley-Leverett problem) in heterogeneous porous medium. The reservoir properties (porosity, permeability) are treated as random variables. The distribution of these properties can affect dynamic properties such as the fluids saturation, front propagation speed or breakthrough time. We explore and use to our advantage the ability of networks to interpolate complex high dimensional functions. We observe that the additional dimensions resulting from a stochastic treatment of the partial differential equations tend to produce smoother solutions on quantities of interest (distributions parameters) which is shown to improve the performance of PINNS. We show that provided a proper parameterization of the uncertainty space, PINN can produce solutions that match closely both the ensemble realizations and the stochastic moments. We demonstrate applications for both homogeneous and heterogeneous fields of properties. We are able to solve problems that can be challenging for classical methods. This approach gives rise to trained models that are both more robust to variations in the input space and can compete in performance with traditional stochastic sampling methods.

MTBF Model for AVs -- From Perception Errors to Vehicle-Level Failures

The development of Automated Vehicles (AVs) is progressing quickly and the first robotaxi services are being deployed worldwide. However, to receive authority certification for mass deployment, manufactures need to justify that their AVs operate safer than human drivers. This in turn creates the need to estimate and model the collision rate (failure rate) of an AV taking all possible errors and driving situations into account. In other words, there is the strong demand for comprehensive Mean Time Between Failure (MTBF) models for AVs. In this paper, we will introduce such a generic and scalable model that creates a link between errors in the perception system to vehicle-level failures (collisions). Using this model, we are able to derive requirements for the perception quality based on the desired vehicle-level MTBF or vice versa to obtain an MTBF value given a certain mission profile and perception quality.

Optimizing UAV Recharge Scheduling for Heterogeneous and Persistent Aerial Service

The adoption of UAVs in communication networks is becoming reality thanks to the deployment of advanced solutions for connecting UAVs and using them as communication relays. However, the use of UAVs introduces novel energy constraints and scheduling challenges in the dynamic management of network devices, due to the need to call back and recharge, or substitute, UAVs that run out of energy. In this paper, we design UAV recharging schemes under realistic assumptions on limited flight times and time consuming charging operations. Such schemes are designed to minimize the size of the fleet to be devoted to a persistent service of a set of aerial locations, hence its cost. We consider a fleet of homogeneous UAVs both under homogeneous and heterogeneous service topologies. For UAVs serving aerial locations with homogeneous distances to a recharge station, we design a simple scheduling, that we name HORR, which we prove to be feasible and optimal, in the sense that it uses the minimum possible number of UAVs to guarantee the coverage of the aerial service locations. For the case of non-evenly distributed aerial locations, we demonstrate that the problem becomes NP-hard, and design a lightweight recharging scheduling scheme, PHERR, that extends the operation of HORR to the heterogeneous case, leveraging the partitioning of the set of service locations. We show that PHERR is near-optimal because it approaches the performance limits identified through a lower bound that we formulate on the total fleet size.

Individual Fairness Guarantees for Neural Networks

We consider the problem of certifying the individual fairness (IF) of feed-forward neural networks (NNs). In particular, we work with the $\epsilon$-$\delta$-IF formulation, which, given a NN and a similarity metric learnt from data, requires that the output difference between any pair of $\epsilon$-similar individuals is bounded by a maximum decision tolerance $\delta \geq 0$. Working with a range of metrics, including the Mahalanobis distance, we propose a method to overapproximate the resulting optimisation problem using piecewise-linear functions to lower and upper bound the NN's non-linearities globally over the input space. We encode this computation as the solution of a Mixed-Integer Linear Programming problem and demonstrate that it can be used to compute IF guarantees on four datasets widely used for fairness benchmarking. We show how this formulation can be used to encourage models' fairness at training time by modifying the NN loss, and empirically confirm our approach yields NNs that are orders of magnitude fairer than state-of-the-art methods.

Finding Global Homophily in Graph Neural Networks When Meeting Heterophily

We investigate graph neural networks on graphs with heterophily. Some existing methods amplify a node's neighborhood with multi-hop neighbors to include more nodes with homophily. However, it is a significant challenge to set personalized neighborhood sizes for different nodes. Further, for other homophilous nodes excluded in the neighborhood, they are ignored for information aggregation. To address these problems, we propose two models GloGNN and GloGNN++, which generate a node's embedding by aggregating information from global nodes in the graph. In each layer, both models learn a coefficient matrix to capture the correlations between nodes, based on which neighborhood aggregation is performed. The coefficient matrix allows signed values and is derived from an optimization problem that has a closed-form solution. We further accelerate neighborhood aggregation and derive a linear time complexity. We theoretically explain the models' effectiveness by proving that both the coefficient matrix and the generated node embedding matrix have the desired grouping effect. We conduct extensive experiments to compare our models against 11 other competitors on 15 benchmark datasets in a wide range of domains, scales and graph heterophilies. Experimental results show that our methods achieve superior performance and are also very efficient.

V4D: Voxel for 4D Novel View Synthesis

Neural radiance fields have made a remarkable breakthrough in the novel view synthesis task at the 3D static scene. However, for the 4D circumstance (e.g., dynamic scene), the performance of the existing method is still limited by the capacity of the neural network, typically in a multilayer perceptron network (MLP). In this paper, we present the method to model the 4D neural radiance field by the 3D voxel, short as V4D, where the 3D voxel has two formats. The first one is to regularly model the bounded 3D space and then use the sampled local 3D feature with the time index to model the density field and the texture field. The second one is in look-up tables (LUTs) format that is for the pixel-level refinement, where the pseudo-surface produced by the volume rendering is utilized as the guidance information to learn a 2D pixel-level refinement mapping. The proposed LUTs-based refinement module achieves the performance gain with a little computational cost and could serve as the plug-and-play module in the novel view synthesis task. Moreover, we propose a more effective conditional positional encoding toward the 4D data that achieves performance gain with negligible computational burdens. Extensive experiments demonstrate that the proposed method achieves state-of-the-art performance by a large margin. At last, the proposed V4D is also a computational-friendly method in both the training and testing phase, where we achieve 2 times faster in the training phase and 10 times faster in the inference phase compared with the state-of-the-art method.

Time series classification for predictive maintenance on event logs

Time series classification (TSC) gained a lot of attention in the pastdecade and number of methods for representing and classifying time series havebeen proposed. Nowadays, methods based on convolutional networks and ensembletechniques represent the state of the art for time series classification. Techniquestransforming time series to image or text also provide reliable ways to extractmeaningful features or representations of time series. We compare the state-of-the-art representation and classification methods on a specific application, thatis predictive maintenance from sequences of event logs. The contributions of thispaper are twofold: introducing a new data set for predictive maintenance on auto-mated teller machines (ATMs) log data and comparing the performance of differentrepresentation methods for predicting the occurrence of a breakdown. The prob-lem is difficult since unlike the classic case of predictive maintenance via signalsfrom sensors, we have sequences of discrete event logs occurring at any time andthe lengths of the sequences, corresponding to life cycles, vary a lot.