Newly arriving nodes in dynamics networks would gradually make the node embedding space drifted and the retraining of node embedding and downstream models indispensable. An exact threshold size of these new nodes, below which the node embedding space will be predicatively maintained, however, is rarely considered in either theory or experiment. From the view of matrix perturbation theory, a threshold of the maximum number of new nodes that keep the node embedding space approximately equivalent is analytically provided and empirically validated. It is therefore theoretically guaranteed that as the size of newly arriving nodes is below this threshold, embeddings of these new nodes can be quickly derived from embeddings of original nodes. A generation framework, Space-Invariant Projection (SIP), is accordingly proposed to enables arbitrary static MF-based embedding schemes to embed new nodes in dynamics networks fast. The time complexity of SIP is linear with the network size. By combining SIP with four state-of-the-art MF-based schemes, we show that SIP exhibits not only wide adaptability but also strong empirical performance in terms of efficiency and efficacy on the node classification task in three real datasets.

Graph-based algorithms have demonstrated state-of-the-art performance in the nearest neighbor search (NN-Search) problem. These empirical successes urge the need for theoretical results that guarantee the search quality and efficiency of these algorithms. However, there exists a practice-to-theory gap in the graph-based NN-Search algorithms. Current theoretical literature focuses on greedy search on exact near neighbor graph while practitioners use approximate near neighbor graph (ANN-Graph) to reduce the preprocessing time. This work bridges this gap by presenting the theoretical guarantees of solving NN-Search via greedy search on ANN-Graph for low dimensional and dense vectors. To build this bridge, we leverage several novel tools from computational geometry. Our results provide quantification of the trade-offs associated with the approximation while building a near neighbor graph. We hope our results will open the door for more provable efficient graph-based NN-Search algorithms.

Advanced real-time location systems (RTLS) allow for collecting spatio-temporal data from human movement behaviours. Tracking individuals in small areas such as schoolyards or nursing homes might impose difficulties for RTLS in terms of positioning accuracy. However, to date, few studies have investigated the performance of different localisation systems regarding the classification of human movement patterns in small areas. The current study aims to design and evaluate an automated framework to classify human movement trajectories obtained from two different RTLS: Global Navigation Satellite System (GNSS) and Ultra-wideband (UWB), in areas of approximately 100 square meters. Specifically, we designed a versatile framework which takes GNSS or UWB data as input, extracts features from these data and classifies them according to the annotated spatial patterns. The automated framework contains three choices for applying noise removal: (i) no noise removal, (ii) Savitzky Golay filter on the raw location data or (iii) Savitzky Golay filter on the extracted features, as well as three choices regarding the classification algorithm: Decision Tree (DT), Random Forest (RF) or Support Vector Machine (SVM). We integrated different stages within the framework with the Sequential Model-Based Algorithm Configuration (SMAC) to perform automated hyperparameter optimisation. The best performance is achieved with a pipeline consisting of noise removal applied to the raw location data with an RF model for the GNSS and no noise removal with an SVM model for the UWB. We further demonstrate through statistical analysis that the UWB achieves significantly higher results than the GNSS in classifying movement patterns.

We introduce a machine learning-powered course allocation mechanism. Concretely, we extend the state-of-the-art Course Match mechanism with a machine learning-based preference elicitation module. In an iterative, asynchronous manner, this module generates pairwise comparison queries that are tailored to each individual student. Regarding incentives, our machine learning-powered course match (MLCM) mechanism retains the attractive strategyproofness in the large property of Course Match. Regarding welfare, we perform computational experiments using a simulator that was fitted to real-world data. Our results show that, compared to Course Match, MLCM increases average student utility by 4%-9% and minimum student utility by 10%-21%, even with only ten comparison queries. Finally, we highlight the practicability of MLCM and the ease of piloting it for universities currently using Course Match.

Knowledge distillation is one of the primary methods of transferring knowledge from large to small models. However, it requires massive task-specific data, which may not be plausible in many real-world applications. Data augmentation methods such as representation interpolation, token replacement, or augmentation with models are applied to tackle this problem. However, these data augmentation methods either potentially cause shifts in decision boundaries (representation interpolation), are not expressive enough (token replacement), or introduce too much computational overhead (augmentation with models). To this end, we propose AugPro (Augmentation with Projection), an effective and efficient data augmentation method for distillation. Our method builds on top of representation interpolation augmentation methods to maintain the diversity of expressions and converts the augmented data to tokens to avoid shifting decision boundaries. It uses simple operations that come with little computational overhead. The results on multiple GLUE tasks show that our methods can improve distillation performance by a large margin at a low time cost. Codes are available at https://github.com/google-research/google-research/tree/master/augpro.

Aspectual meaning refers to how the internal temporal structure of situations is presented. This includes whether a situation is described as a state or as an event, whether the situation is finished or ongoing, and whether it is viewed as a whole or with a focus on a particular phase. This survey gives an overview of computational approaches to modeling lexical and grammatical aspect along with intuitive explanations of the necessary linguistic concepts and terminology. In particular, we describe the concepts of stativity, telicity, habituality, perfective and imperfective, as well as influential inventories of eventuality and situation types. We argue that because aspect is a crucial component of semantics, especially when it comes to reporting the temporal structure of situations in a precise way, future NLP approaches need to be able to handle and evaluate it systematically in order to achieve human-level language understanding.

Deep Neural Networks (DNNs) outshine alternative function approximators in many settings thanks to their modularity in composing any desired differentiable operator. The formed parametrized functional is then tuned to solve a task at hand from simple gradient descent. This modularity comes at the cost of making strict enforcement of constraints on DNNs, e.g. from a priori knowledge of the task, or from desired physical properties, an open challenge. In this paper we propose the first provable affine constraint enforcement method for DNNs that only requires minimal changes into a given DNN's forward-pass, that is computationally friendly, and that leaves the optimization of the DNN's parameter to be unconstrained, i.e. standard gradient-based method can be employed. Our method does not require any sampling and provably ensures that the DNN fulfills the affine constraint on a given input space's region at any point during training, and testing. We coin this method POLICE, standing for Provably Optimal LInear Constraint Enforcement. Github: https://github.com/RandallBalestriero/POLICE

The National Football League (NFL) Scouting Combine serves as a tool to evaluate the skills of prospective players and assess their readiness to play in the NFL. The development of machine learning brings new opportunities in assessing the utility of the Scouting Combine. Using machine and statistical learning, it may be possible to predict future success of prospective athletes, as well as predict which Scouting Combine tests are the most important. Results from statistical learning research have been contradicting whether the Scouting combine is a useful metric for player success. In this study, we investigate if machine learning can be used to determine matriculation and future success in the NFL. Using Scouting Combine data, we evaluate six different algorithms' ability to predict whether a potential draft pick will play a single NFL snap (matriculation). If a player is drafted, we predict how many snaps they go on to play (success). We are able to predict matriculation with 83% accuracy; however, we are unable to predict later success. Our best performing algorithm returns large error and low explained variance (RMSE=1,210 snaps; ${R}^2$=0.17). These findings indicate that while the Scouting Combine can predict NFL matriculation, it may not be a reliable predictor of long-term player success.

Due to the gap between a substitute model and a victim model, the gradient-based noise generated from a substitute model may have low transferability for a victim model since their gradients are different. Inspired by the fact that the decision boundaries of different models do not differ much, we conduct experiments and discover that the gradients of different models are more similar on the decision boundary than in the original position. Moreover, since the decision boundary in the vicinity of an input image is flat along most directions, we conjecture that the boundary gradients can help find an effective direction to cross the decision boundary of the victim models. Based on it, we propose a Boundary Fitting Attack to improve transferability. Specifically, we introduce a method to obtain a set of boundary points and leverage the gradient information of these points to update the adversarial examples. Notably, our method can be combined with existing gradient-based methods. Extensive experiments prove the effectiveness of our method, i.e., improving the success rate by 5.6% against normally trained CNNs and 14.9% against defense CNNs on average compared to state-of-the-art transfer-based attacks. Further we compare transformers with CNNs, the results indicate that transformers are more robust than CNNs. However, our method still outperforms existing methods when attacking transformers. Specifically, when using CNNs as substitute models, our method obtains an average attack success rate of 58.2%, which is 10.8% higher than other state-of-the-art transfer-based attacks.

There is increasing interest to work with user generated content in social media, especially textual posts over time. Currently there is no consistent way of segmenting user posts into timelines in a meaningful way that improves the quality and cost of manual annotation. Here we propose a set of methods for segmenting longitudinal user posts into timelines likely to contain interesting moments of change in a user's behaviour, based on their online posting activity. We also propose a novel framework for evaluating timelines and show its applicability in the context of two different social media datasets. Finally, we present a discussion of the linguistic content of highly ranked timelines.