The data scarcity problem in Electroencephalography (EEG) based affective computing results into difficulty in building an effective model with high accuracy and stability using machine learning algorithms especially deep learning models. Data augmen
tation has recently achieved considerable performance improvement for deep learning models: increased accuracy, stability, and reduced over-fitting. In this paper, we propose a novel data augmentation framework, namely Generative Adversarial Network-based Self-supervised Data Augmentation (GANSER). As the first to combine adversarial training with self-supervised learning for EEG-based emotion recognition, the proposed framework can generate high-quality and high-diversity simulated EEG samples. In particular, we utilize adversarial training to learn an EEG generator and force the generated EEG signals to approximate the distribution of real samples, ensuring the quality of augmented samples. A transformation function is employed to mask parts of EEG signals and force the generator to synthesize potential EEG signals based on the remaining parts, to produce a wide variety of samples. The masking possibility during transformation is introduced as prior knowledge to guide to extract distinguishable features for simulated EEG signals and generalize the classifier to the augmented sample space. Finally, extensive experiments demonstrate our proposed method can help emotion recognition for performance gain and achieve state-of-the-art results.
Hash table is a fundamental data structure for quick search and retrieval of data. It is a key component in complex graph analytics and AI/ML applications. State-of-the-art parallel hash table implementations either make some simplifying assumptions
such as supporting only a subset of hash table operations or employ optimizations that lead to performance that is highly data dependent and in the worst case can be similar to a sequential implementation. In contrast, in this work we develop a dynamic hash table that supports all the hash table queries - search, insert, delete, update, while allowing us to support p parallel queries (p>1) per clock cycle via p processing engines (PEs) in the worst case i.e. the performance is data agnostic. We achieve this by implementing novel XOR based multi-ported block memories on FPGAs. Additionally, we develop a technique to optimize the memory requirement of the hash table if the ratio of search to insert/update/delete queries is known beforehand. We implement our design on state-of-the-art FPGA devices. Our design is scalable to 16 PEs and supports throughput up to 5926 MOPS. It matches the throughput of the state-of-the-art hash table design - FASTHash, which only supports search and insert operations. Comparing with the best FPGA design that supports the same set of operations, our hash table achieves up to 12.3x speedup.
Contrastive learning has revolutionized self-supervised image representation learning field, and recently been adapted to video domain. One of the greatest advantages of contrastive learning is that it allows us to flexibly define powerful loss objec
tives as long as we can find a reasonable way to formulate positive and negative samples to contrast. However, existing approaches rely heavily on the short-range spatiotemporal salience to form clip-level contrastive signals, thus limit themselves from using global context. In this paper, we propose a new video-level contrastive learning method based on segments to formulate positive pairs. Our formulation is able to capture global context in a video, thus robust to temporal content change. We also incorporate a temporal order regularization term to enforce the inherent sequential structure of videos. Extensive experiments show that our video-level contrastive learning framework (VCLR) is able to outperform previous state-of-the-arts on five video datasets for downstream action classification, action localization and video retrieval. Code is available at https://github.com/amazon-research/video-contrastive-learning.
To accommodate the advent of microgrids (MG) managing distributed energy resources (DER) in distribution systems, an interactive two-stage joint retail electricity market mechanism is proposed to provide an effective platform for these prosumers to p
roactively join in retail transactions. Day-ahead stochastic energy trading between the distribution system operator (DSO) and MGs is conducted in the first stage of a centralized retail market, where a chance-constrained uncertainty distribution locational marginal price (CC-UDLMP) containing the cost of uncertainty precautions is used to settle transactions. In the second stage, a novel intra-day peer-to-peer-based (P2P) flexibility transaction pattern is implemented between MGs in local flexibility markets under the regulation of DSO to eliminate power imbalances caused by rolling-based estimates whilst considering systematic operations. A fully distributed iterative algorithm is presented to find the equilibrium solution of this two-stage sequential game framework. Moreover, in order to enhance the versatility of this algorithm, an improved Lp-box alternating direction methods of multipliers (ADMM) algorithm is used to efficiently resolve the first-stage stochastic economic dispatch problem with a mixed-integer second-order cone structure. It is verified that the proposed market mechanism can effectively improve the overall market efficiency under uncertainties.
The surge in the number of books published makes the manual evaluation methods difficult to efficiently evaluate books. The use of books citations and alternative evaluation metrics can assist manual evaluation and reduce the cost of evaluation. Howe
ver, most existing evaluation research was based on a single evaluation source with coarse-grained analysis, which may obtain incomprehensive or one-sided evaluation results of book impact. Meanwhile, relying on a single resource for book assessment may lead to the risk that the evaluation results cannot be obtained due to the lack of the evaluation data, especially for newly published books. Hence, this paper measured book impact based on an evaluation system constructed by integrating multiple evaluation sources. Specifically, we conducted finer-grained mining on the multiple evaluation sources, including books internal evaluation resources and external evaluation resources. Various technologies (e.g. topic extraction, sentiment analysis, text classification) were used to extract corresponding evaluation metrics from the internal and external evaluation resources. Then, Expert evaluation combined with analytic hierarchy process was used to integrate the evaluation metrics and construct a book impact evaluation system. Finally, the reliability of the evaluation system was verified by comparing with the results of expert evaluation, detailed and diversified evaluation results were then obtained. The experimental results reveal that differential evaluation resources can measure the books impacts from different dimensions, and the integration of multiple evaluation data can assess books more comprehensively. Meanwhile, the book impact evaluation system can provide personalized evaluation results according to the users evaluation purposes. In addition, the disciplinary differences should be considered for assessing books impacts.
We develop a neuroevolution-potential (NEP) framework for generating neural network based machine-learning potentials. They are trained using an evolutionary strategy for performing large-scale molecular dynamics (MD) simulations. A descriptor of the
atomic environment is constructed based on Chebyshev and Legendre polynomials. The method is implemented in graphic processing units within the open-source GPUMD package, which can attain a computational speed over $10^7$ atom-step per second using one Nvidia Tesla V100. Furthermore, per-atom heat current is available in NEP, which paves the way for efficient and accurate MD simulations of heat transport in materials with strong phonon anharmonicity or spatial disorder, which usually cannot be accurately treated either with traditional empirical potentials or with perturbative methods.
Recently, Vision Transformers (ViTs) have achieved impressive results on various vision tasks. Yet, their generalization ability under different distribution shifts is rarely understood. In this work, we provide a comprehensive study on the out-of-di
stribution generalization of ViTs. To support a systematic investigation, we first present a taxonomy of distribution shifts by categorizing them into five conceptual groups: corruption shift, background shift, texture shift, destruction shift, and style shift. Then we perform extensive evaluations of ViT variants under different groups of distribution shifts and compare their generalization ability with CNNs. Several important observations are obtained: 1) ViTs generalize better than CNNs under multiple distribution shifts. With the same or fewer parameters, ViTs are ahead of corresponding CNNs by more than 5% in top-1 accuracy under most distribution shifts. 2) Larger ViTs gradually narrow the in-distribution and out-of-distribution performance gap. To further improve the generalization of ViTs, we design the Generalization-Enhanced ViTs by integrating adversarial learning, information theory, and self-supervised learning. By investigating three types of generalization-enhanced ViTs, we observe their gradient-sensitivity and design a smoother learning strategy to achieve a stable training process. With modified training schemes, we achieve improvements on performance towards out-of-distribution data by 4% from vanilla ViTs. We comprehensively compare three generalization-enhanced ViTs with their corresponding CNNs, and observe that: 1) For the enhanced model, larger ViTs still benefit more for the out-of-distribution generalization. 2) generalization-enhanced ViTs are more sensitive to the hyper-parameters than corresponding CNNs. We hope our comprehensive study could shed light on the design of more generalizable learning architectures.
The operation of adding edges has been frequently used to the study of opinion dynamics in social networks for various purposes. In this paper, we consider the edge addition problem for the DeGroot model of opinion dynamics in a social network with $
n$ nodes and $m$ edges, in the presence of a small number $s ll n$ of competing leaders with binary opposing opinions 0 or 1. Concretely, we pose and investigate the problem of maximizing the equilibrium overall opinion by creating $k$ new edges in a candidate edge set, where each edge is incident to a 1-valued leader and a follower node. We show that the objective function is monotone and submodular. We then propose a simple greedy algorithm with an approximation factor $(1-frac{1}{e})$ that approximately solves the problem in $O(n^3)$ time. Moreover, we provide a fast algorithm with a $(1-frac{1}{e}-epsilon)$ approximation ratio and $tilde{O}(mkepsilon^{-2})$ time complexity for any $epsilon>0$, where $tilde{O}(cdot)$ notation suppresses the ${rm poly} (log n)$ factors. Extensive experiments demonstrate that our second approximate algorithm is efficient and effective, which scales to large networks with more than a million nodes.
As a fundamental research object, the minimum edge dominating set (MEDS) problem is of both theoretical and practical interest. However, determining the size of a MEDS and the number of all MEDSs in a general graph is NP-hard, and it thus makes sense
to find special graphs for which the MEDS problem can be exactly solved. In this paper, we study analytically the MEDS problem in the pseudofractal scale-free web and the Sierpinski gasket with the same number of vertices and edges. For both graphs, we obtain exact expressions for the edge domination number, as well as recursive solutions to the number of distinct MEDSs. In the pseudofractal scale-free web, the edge domination number is one-ninth of the number of edges, which is three-fifths of the edge domination number of the Sierpinski gasket. Moreover, the number of all MEDSs in the pseudofractal scale-free web is also less than that corresponding to the Sierpinski gasket. We argue that the difference of the size and number of MEDSs between the two studied graphs lies in the scale-free topology.
Present language understanding methods have demonstrated extraordinary ability of recognizing patterns in texts via machine learning. However, existing methods indiscriminately use the recognized patterns in the testing phase that is inherently diffe
rent from us humans who have counterfactual thinking, e.g., to scrutinize for the hard testing samples. Inspired by this, we propose a Counterfactual Reasoning Model, which mimics the counterfactual thinking by learning from few counterfactual samples. In particular, we devise a generation module to generate representative counterfactual samples for each factual sample, and a retrospective module to retrospect the model prediction by comparing the counterfactual and factual samples. Extensive experiments on sentiment analysis (SA) and natural language inference (NLI) validate the effectiveness of our method.
