Understanding generalization and robustness of machine learning models fundamentally relies on assuming an appropriate metric on the data space. Identifying such a metric is particularly challenging for non-Euclidean data such as graphs. Here, we propose a pseudometric for attributed graphs, the Tree Mover's Distance (TMD), and study its relation to generalization. Via a hierarchical optimal transport problem, TMD reflects the local distribution of node attributes as well as the distribution of local computation trees, which are known to be decisive for the learning behavior of graph neural networks (GNNs). First, we show that TMD captures properties relevant for graph classification: a simple TMD-SVM can perform competitively with standard GNNs. Second, we relate TMD to generalization of GNNs under distribution shifts, and show that it correlates well with performance drop under such shifts.

Africa pose, partial view, color diapers The Americas vs. Africa pose, color, partial view pet foods Asia vs.

Overall the paper reads like a nice combination of existing tricks, and provides very convincing experimental results. Strengths of the paper are simplicity and a relatively straightforward idea, but not trivial to implement/test. The experimental section is therefore a strong part of this paper. Things to improve: handle better the interplay between regularized/not regularized formulations, be more rigorous with maths (computations/notations are a bit sloppy) and ideally provide an algorithmic box to see more clearly into what the authors propose. A few minor comments: - In Eq.1, the Euclidean distance between word embeddings is used as a cost, in Eq.6, for the purpose of Malahanobis metric learning, that cost becomes the squared euclidean metric (and thus what is usually referred to as 2-Wasserstein).

Integrating Unmanned Aerial Vehicles (UAVs) with Unmanned Ground Vehicles (UGVs) provides an effective solution for persistent surveillance in disaster management. UAVs excel at covering large areas rapidly, but their range is limited by battery capacity. UGVs, though slower, can carry larger batteries for extended missions. By using UGVs as mobile recharging stations, UAVs can extend mission duration through periodic refueling, leveraging the complementary strengths of both systems. To optimize this energy-aware UAV-UGV cooperative routing problem, we propose a planning framework that determines optimal routes and recharging points between a UAV and a UGV. Our solution employs a deep reinforcement learning (DRL) framework built on an encoder-decoder transformer architecture with multi-head attention mechanisms. This architecture enables the model to sequentially select actions for visiting mission points and coordinating recharging rendezvous between the UAV and UGV. The DRL model is trained to minimize the age periods (the time gap between consecutive visits) of mission points, ensuring effective surveillance. We evaluate the framework across various problem sizes and distributions, comparing its performance against heuristic methods and an existing learning-based model. Results show that our approach consistently outperforms these baselines in both solution quality and runtime. Additionally, we demonstrate the DRL policy's applicability in a real-world disaster scenario as a case study and explore its potential for online mission planning to handle dynamic changes. Adapting the DRL policy for priority-driven surveillance highlights the model's generalizability for real-time disaster response.

The authors introduce a new variation of GAN that is claimed to be suitable for text generation. The proposed method relies on a new optimal transport–based distance metric on the feature space learned by the "discriminator". The idea is sound and seems to be novel. The text is well written and easy to follow. Overall, I like the ideas in the paper but I think that the experiments are not robust, which makes it difficult to judge if the current method represents a real advance over the previous GAN models for text generation. Some questions/comments about the experiments: (1) For the generic text generation, why not using datasets that have been used in other works: Penn Treebank, IMDB? (2) For generic text generation why the authors have not compared their results with MaskGAN?

Although access control based on human face recognition has become popular in consumer applications, it still has several implementation issues before it can realize a stand-alone access control system. Owing to a lack of computational resources, lightweight and computationally efficient face recognition algorithms are required. The conventional access control systems require significant active cooperation from the users despite its non-aggressive nature. The lighting/illumination change is one of the most difficult and challenging problems for human-face-recognition-based access control applications. This paper presents the design and implementation of a user-friendly, stand-alone access control system based on human face recognition at a distance. The local binary pattern (LBP)-AdaBoost framework was employed for face and eyes detection, which is fast and invariant to illumination changes. It can detect faces and eyes of varied sizes at a distance. For fast face recognition with a high accuracy, the Gabor-LBP histogram framework was modified by substituting the Gabor wavelet with Gaussian derivative filters, which reduced the facial feature size by 40% of the Gabor-LBP-based facial features, and was robust to significant illumination changes and complicated backgrounds. The experiments on benchmark datasets produced face recognition accuracies of 97.27% on an E-face dataset and 99.06% on an XM2VTS dataset, respectively. The system achieved a 91.5% true acceptance rate with a 0.28% false acceptance rate and averaged a 5.26 frames/sec processing speed on a newly collected face image and video dataset in an indoor office environment.

K-nearest neighbors (KNN) is a type of supervised learning machine learning algorithm and is used for both regression and classification tasks. KNN is used to make predictions on the test data set based on the characteristics of the current training data points. This is done by calculating the distance between the test data and training data, assuming that similar things exist within close proximity. The algorithm will have stored learned data, making it more effective at predicting and categorising new data points. When a new data point is inputted, the KNN algorithm will learn its characteristics/features.

For example, suppose you want to build a simple linear regression model using an m-dimensional training data set. If the model uses the gradient descent algorithm to minimize the objective function in order to determine the weights w_0, w_1, w_2, …,w_m, then we can have an optimizer such as GradientDescent(eta, n_iter). Here eta (learning rate) and n_iter (number of iterations) are the hyperparameters that would have to be adjusted in order to obtain the best values for the model parameters w_0, w_1, w_2, …,w_m. For more information about this, see the following example: Machine Learning: Python Linear Regression Estimator Using Gradient Descent. Here, n_iter is the number of iterations, eta0 is the learning rate, and random_state is the seed of the pseudo random number generator to use when shuffling the data.

For example, suppose you want to build a simple linear regression model using an m-dimensional training data set. If the model uses the gradient descent algorithm to minimize the objective function in order to determine the weights w_0, w_1, w_2, …,w_m, then we can have an optimizer such as GradientDescent(eta, n_iter). Here eta (learning rate) and n_iter (number of iterations) are the hyperparameters that would have to be adjusted in order to obtain the best values for the model parameters w_0, w_1, w_2, …,w_m. For more information about this, see the following example: Machine Learning: Python Linear Regression Estimator Using Gradient Descent. Here, n_iter is the number of iterations, eta0 is the learning rate, and eed of the pseudo random number generator to use when shuffling the data.

At the core of cluster analysis is the concept of measuring distances between a variety of different data point dimensions. For example, when considering k-means clustering, there is a need to measure a) distances between individual data point dimensions and the corresponding cluster centroid dimensions of all clusters, and b) distances between cluster centroid dimensions and all resulting cluster member data point dimensions. While k-means, the simplest and most prominent clustering algorithm, generally uses Euclidean distance as its similarity distance measurement, contriving innovative or variant clustering algorithms which, among other alterations, utilize different distance measurements is not a stretch. It is thus a judgment of orientation and not magnitude: two vectors with the same orientation have a cosine similarity of 1, two vectors at 90 have a similarity of 0, and two vectors diametrically opposed have a similarity of -1, independent of their magnitude.