This paper introduces a novel metaheuristic algorithm, known as the efficient multiplayer battle game optimizer (EMBGO), specifically designed for addressing complex numerical optimization tasks. The motivation behind this research stems from the need to rectify identified shortcomings in the original MBGO, particularly in search operators during the movement phase, as revealed through ablation experiments. EMBGO mitigates these limitations by integrating the movement and battle phases to simplify the original optimization framework and improve search efficiency. Besides, two efficient search operators: differential mutation and L\'evy flight are introduced to increase the diversity of the population. To evaluate the performance of EMBGO comprehensively and fairly, numerical experiments are conducted on benchmark functions such as CEC2017, CEC2020, and CEC2022, as well as engineering problems. Twelve well-established MA approaches serve as competitor algorithms for comparison. Furthermore, we apply the proposed EMBGO to the complex adversarial robust neural architecture search (ARNAS) tasks and explore its robustness and scalability. The experimental results and statistical analyses confirm the efficiency and effectiveness of EMBGO across various optimization tasks. As a potential optimization technique, EMBGO holds promise for diverse applications in real-world problems and deep learning scenarios. The source code of EMBGO is made available in \url{//github.com/RuiZhong961230/EMBGO}.
相關內容
Computer programs containing calls to linear solvers are a known challenge for automatic differentiation. Previous publications advise against differentiating through the low-level solver implementation, and instead advocate for high-level approaches that express the derivative in terms of a modified linear system that can be solved with a separate solver call. Despite this ubiquitous advice, we are not aware of prior work comparing the accuracy of both approaches. With this article we thus empirically study a simple question: What happens if we ignore common wisdom, and differentiate through linear solvers?
This paper introduces a uniform substitution calculus for differential refinement logic dRL. The logic dRL extends the differential dynamic logic dL such that one can simultaneously reason about properties of and relations between hybrid systems. Refinements is useful e.g. for simplifying proofs by relating a concrete hybrid system to an abstract one from which the property can be proved more easily. Uniform substitution is the key to parsimonious prover microkernels. It enables the verbatim use of single axiom formulas instead of axiom schemata with soundness-critical side conditions scattered across the proof calculus. The uniform substitution rule can then be used to instantiate all axioms soundly. Access to differential variables in dRL enables more control over the notion of refinement, which is shown to be decidable on a fragment of hybrid programs.
In autonomous robotics, a critical challenge lies in developing robust solutions for Active Collaborative SLAM, wherein multiple robots collaboratively explore and map an unknown environment while intelligently coordinating their movements and sensor data acquisitions. In this article, we present an approach for coordinating a system consisting of multiple robots to perform Active Collaborative SLAM (AC-SLAM) for environmental exploration. Our method efficiently spreads the robots for maximum exploration while keeping SLAM uncertainty low. Additionally, We also present two coordination approaches, synchronous and asynchronous to prioritize robot goal assignments by the central server. The proposed method is implemented in ROS and evaluated through simulation and experiments on publicly available datasets and similar methods, rendering promising results.
Decentralized Finance enables many novel applications that were impossible in traditional finances. However, it also introduces new types of vulnerabilities, such as composability bugs. The composability bugs refer to issues that lead to erroneous behaviors when multiple smart contracts operate together. One typical example of composability bugs is those between token contracts and Constant Product Market Makers (CPMM), the most widely used model for Decentralized Exchanges. Since 2022, 23 exploits of such kind have resulted in a total loss of 2.2M USD. BlockSec, a smart contract auditing company, once reported that 138 exploits of such kind occurred just in February 2023. We propose CPMM-Exploiter, which automatically detects and generates end-to-end exploits for CPMM composability bugs. Generating such end-to-end exploits is challenging due to the large search space of multiple contracts and various fees involved with financial services. To tackle this, we investigated real-world exploits regarding these vulnerabilities and identified that they arise due to violating two safety invariants. Based on this observation, we implemented CPMM-Exploiter, a new grammar-based fuzzer targeting the detection of these bugs. CPMM-Exploiter uses fuzzing to find transactions that break the invariants. It then refines these transactions to make them profitable for the attacker. We evaluated CPMM-Exploiter on two real-world exploit datasets. CPMM-Exploiter obtained recalls of 0.91 and 0.89, respectively, while five baselines achieved maximum recalls of 0.36 and 0.58, respectively. We further evaluated CPMM-Exploiter by running it on the latest blocks of the Ethereum and Binance networks. It successfully generated 18 new exploits, which can result in 12.9K USD profit in total.
Nowadays, personalized recommender systems play an increasingly important role in music scenarios in our daily life with the preference prediction ability. However, existing methods mainly rely on users' implicit feedback (e.g., click, dwell time) which ignores the detailed user experience. This paper introduces Electroencephalography (EEG) signals to personal music preferences as a basis for the personalized recommender system. To realize collection in daily life, we use a dry-electrodes portable device to collect data. We perform a user study where participants listen to music and record preferences and moods. Meanwhile, EEG signals are collected with a portable device. Analysis of the collected data indicates a significant relationship between music preference, mood, and EEG signals. Furthermore, we conduct experiments to predict personalized music preference with the features of EEG signals. Experiments show significant improvement in rating prediction and preference classification with the help of EEG. Our work demonstrates the possibility of introducing EEG signals in personal music preference with portable devices. Moreover, our approach is not restricted to the music scenario, and the EEG signals as explicit feedback can be used in personalized recommendation tasks.
Localization of computations plays a crucial role in solving hard problems efficiently. We will refer to the techniques implementing such localization as ${\mathit local}$ ${\mathit computing}$. We relate local computing with $\mathit{partial}$ $\mathit{quantifier}$ $\mathit{elimination}$ (PQE). The latter is a generalization of regular quantifier elimination where one can take a $\mathit{part}$ of the formula out of the scope of quantifiers. The objective of this paper is to show that PQE can be viewed as a language of local computing and hence building efficient PQE solvers is of great importance. We describe application of local computing by PQE to three different problems of hardware verification: property generation, equivalence checking and model checking. Besides, we discuss using local computing by PQE for SAT solving. Finally, we relate PQE and interpolation, a form of local computing.
Recently, graph neural networks (GNNs) have been widely used for document classification. However, most existing methods are based on static word co-occurrence graphs without sentence-level information, which poses three challenges:(1) word ambiguity, (2) word synonymity, and (3) dynamic contextual dependency. To address these challenges, we propose a novel GNN-based sparse structure learning model for inductive document classification. Specifically, a document-level graph is initially generated by a disjoint union of sentence-level word co-occurrence graphs. Our model collects a set of trainable edges connecting disjoint words between sentences and employs structure learning to sparsely select edges with dynamic contextual dependencies. Graphs with sparse structures can jointly exploit local and global contextual information in documents through GNNs. For inductive learning, the refined document graph is further fed into a general readout function for graph-level classification and optimization in an end-to-end manner. Extensive experiments on several real-world datasets demonstrate that the proposed model outperforms most state-of-the-art results, and reveal the necessity to learn sparse structures for each document.
Recent contrastive representation learning methods rely on estimating mutual information (MI) between multiple views of an underlying context. E.g., we can derive multiple views of a given image by applying data augmentation, or we can split a sequence into views comprising the past and future of some step in the sequence. Contrastive lower bounds on MI are easy to optimize, but have a strong underestimation bias when estimating large amounts of MI. We propose decomposing the full MI estimation problem into a sum of smaller estimation problems by splitting one of the views into progressively more informed subviews and by applying the chain rule on MI between the decomposed views. This expression contains a sum of unconditional and conditional MI terms, each measuring modest chunks of the total MI, which facilitates approximation via contrastive bounds. To maximize the sum, we formulate a contrastive lower bound on the conditional MI which can be approximated efficiently. We refer to our general approach as Decomposed Estimation of Mutual Information (DEMI). We show that DEMI can capture a larger amount of MI than standard non-decomposed contrastive bounds in a synthetic setting, and learns better representations in a vision domain and for dialogue generation.
In this paper, we propose a novel Feature Decomposition and Reconstruction Learning (FDRL) method for effective facial expression recognition. We view the expression information as the combination of the shared information (expression similarities) across different expressions and the unique information (expression-specific variations) for each expression. More specifically, FDRL mainly consists of two crucial networks: a Feature Decomposition Network (FDN) and a Feature Reconstruction Network (FRN). In particular, FDN first decomposes the basic features extracted from a backbone network into a set of facial action-aware latent features to model expression similarities. Then, FRN captures the intra-feature and inter-feature relationships for latent features to characterize expression-specific variations, and reconstructs the expression feature. To this end, two modules including an intra-feature relation modeling module and an inter-feature relation modeling module are developed in FRN. Experimental results on both the in-the-lab databases (including CK+, MMI, and Oulu-CASIA) and the in-the-wild databases (including RAF-DB and SFEW) show that the proposed FDRL method consistently achieves higher recognition accuracy than several state-of-the-art methods. This clearly highlights the benefit of feature decomposition and reconstruction for classifying expressions.
Emotion plays an important role in detecting fake news online. When leveraging emotional signals, the existing methods focus on exploiting the emotions of news contents that conveyed by the publishers (i.e., publisher emotion). However, fake news is always fabricated to evoke high-arousal or activating emotions of people to spread like a virus, so the emotions of news comments that aroused by the crowd (i.e., social emotion) can not be ignored. Furthermore, it needs to be explored whether there exists a relationship between publisher emotion and social emotion (i.e., dual emotion), and how the dual emotion appears in fake news. In the paper, we propose Dual Emotion Features to mine dual emotion and the relationship between them for fake news detection. And we design a universal paradigm to plug it into any existing detectors as an enhancement. Experimental results on three real-world datasets indicate the effectiveness of the proposed features.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191