Foundation models (FMs) are revolutionizing the analysis and understanding of remote sensing (RS) scenes, including aerial RGB, multispectral, and SAR images. However, hyperspectral images (HSIs), which are rich in spectral information, have not seen much application of FMs, with existing methods often restricted to specific tasks and lacking generality. To fill this gap, we introduce HyperSIGMA, a vision transformer-based foundation model for HSI interpretation, scalable to over a billion parameters. To tackle the spectral and spatial redundancy challenges in HSIs, we introduce a novel sparse sampling attention (SSA) mechanism, which effectively promotes the learning of diverse contextual features and serves as the basic block of HyperSIGMA. HyperSIGMA integrates spatial and spectral features using a specially designed spectral enhancement module. In addition, we construct a large-scale hyperspectral dataset, HyperGlobal-450K, for pre-training, which contains about 450K hyperspectral images, significantly surpassing existing datasets in scale. Extensive experiments on various high-level and low-level HSI tasks demonstrate HyperSIGMA's versatility and superior representational capability compared to current state-of-the-art methods. Moreover, HyperSIGMA shows significant advantages in scalability, robustness, cross-modal transferring capability, and real-world applicability.
相關內容
ACM/IEEE第23屆模型驅動工程語言和系統國際會議，是模型驅動軟件和系統工程的首要會議系列，由ACM-SIGSOFT和IEEE-TCSE支持組織。自1998年以來，模型涵蓋了建模的各個方面，從語言和方法到工具和應用程序。模特的參加者來自不同的背景，包括研究人員、學者、工程師和工業專業人士。MODELS 2019是一個論壇，參與者可以圍繞建模和模型驅動的軟件和系統交流前沿研究成果和創新實踐經驗。今年的版本將為建模社區提供進一步推進建模基礎的機會，并在網絡物理系統、嵌入式系統、社會技術系統、云計算、大數據、機器學習、安全、開源等新興領域提出建模的創新應用以及可持續性。
官網鏈接： ·
INTERACT
·
MoDELS
·
CTR
·
Next
·
Deep & Cross Network and its derivative models have become an important paradigm in click-through rate (CTR) prediction due to their effective balance between computational cost and performance. However, these models face four major limitations: (1) while most models claim to capture high-order feature interactions, they often do so implicitly and non-interpretably through deep neural networks (DNN), which limits the trustworthiness of the model's predictions; (2) the performance of existing explicit feature interaction methods is often weaker than that of implicit DNN, undermining their necessity; (3) many models fail to adaptively filter noise while enhancing the order of feature interactions; (4) the fusion methods of most models cannot provide suitable supervision signals for their different interaction methods. To address the identified limitations, this paper proposes the next generation Deep Cross Network (DCNv3) and Shallow & Deep Cross Network (SDCNv3). These models ensure interpretability in feature interaction modeling while exponentially increasing the order of feature interactions to achieve genuine Deep Crossing rather than just Deep & Cross. Additionally, we employ a Self-Mask operation to filter noise and reduce the number of parameters in the cross network by half. In the fusion layer, we use a simple yet effective loss weight calculation method called Tri-BCE to provide appropriate supervision signals. Comprehensive experiments on six datasets demonstrate the effectiveness, efficiency, and interpretability of DCNv3 and SDCNv3. The code, running logs, and detailed hyperparameter configurations are available at: //anonymous.4open.science/r/DCNv3-E352.
Payment Channel Networks (PCNs) have been proposed as an alternative solution to the scalability, throughput, and cost overhead associated with on-chain transactions. By facilitating offchain execution of transactions, PCNs significantly reduce the burden on the blockchain, leading to faster transaction processing, reduced transaction fees, and enhanced privacy. Despite these advantages, the current research in PCNs presents a variety of research challenges that require further exploration. In this paper, we survey the recent work in several aspects of PCNs, such as pathfinding and routing, virtual channels, state channels, payment channel hubs and rebalancing. This survey aims to provide the reader with a detailed understanding of the current state-of-the-art in PCN research, highlighting a few important advancements. Additionally, we highlight the various unresolved issues in the area of PCN research. Specifically, this paper seeks to answer the following crucial question: What are the various interesting and non-trivial challenges in PCN research that require immediate attention from the academic and research community? By addressing this question, we aim to identify the most pressing problems and future research directions that interested readers can immediately work on. Through this analysis, we hope to inspire researchers and practitioners to tackle these challenges to make PCNs more secure and versatile
As technology advances, the use of Machine Learning (ML) in cybersecurity is becoming increasingly crucial to tackle the growing complexity of cyber threats. While traditional ML models can enhance cybersecurity, their high energy and resource demands limit their applications, leading to the emergence of Tiny Machine Learning (TinyML) as a more suitable solution for resource-constrained environments. TinyML is widely applied in areas such as smart homes, healthcare, and industrial automation. TinyML focuses on optimizing ML algorithms for small, low-power devices, enabling intelligent data processing directly on edge devices. This paper provides a comprehensive review of common challenges of TinyML techniques, such as power consumption, limited memory, and computational constraints; it also explores potential solutions to these challenges, such as energy harvesting, computational optimization techniques, and transfer learning for privacy preservation. On the other hand, this paper discusses TinyML's applications in advancing cybersecurity for Electric Vehicle Charging Infrastructures (EVCIs) as a representative use case. It presents an experimental case study that enhances cybersecurity in EVCI using TinyML, evaluated against traditional ML in terms of reduced delay and memory usage, with a slight trade-off in accuracy. Additionally, the study includes a practical setup using the ESP32 microcontroller in the PlatformIO environment, which provides a hands-on assessment of TinyML's application in cybersecurity for EVCI.
We present Banyan, an improved model to learn semantic representations by inducing explicit structure over data. In contrast to prior approaches using structure spanning single sentences, Banyan learns by resolving multiple constituent structures into a shared one explicitly incorporating global context. Combined with an improved message-passing scheme inspired by Griffin, Banyan learns significantly better representations, avoids spurious false negatives with contrastive learning, and drastically improves memory efficiency in such explicit-structured models. Using the Self-StrAE framework, we show that Banyan (a) outperforms baselines using sentential structure across various settings (b) matches or outperforms unstructured baselines like GloVe (+augmentations) and a RoBERTa medium (+simcse) pre-trained on 100M tokens, despite having just a handful of (non-embedding) parameters, and (c) also learns effective representations across several low resource (Asian and African) languages as measured on SemRel tasks.
Understanding and shaping the behaviour of Large Language Models (LLMs) is increasingly important as applications become more powerful and more frequently adopted. This paper introduces a machine unlearning method specifically designed for LLMs. We introduce a selective pruning method for LLMs that removes neurons based on their relative importance on a targeted capability compared to overall network performance. This approach is a compute- and data-efficient method for identifying and removing neurons that enable specific behaviours. Our findings reveal that both feed-forward and attention neurons in LLMs are specialized; that is, for specific tasks, certain neurons are more crucial than others. Code from all experiments is available at //github.com/nickypro/selective-pruning
We propose Cooperative Component Analysis (CoCA), a new method for unsupervised multi-view analysis: it identifies the component that simultaneously captures significant within-view variance and exhibits strong cross-view correlation. The challenge of integrating multi-view data is particularly important in biology and medicine, where various types of "-omic" data, ranging from genomics to proteomics, are measured on the same set of samples. The goal is to uncover important, shared signals that represent underlying biological mechanisms. CoCA combines an approximation error loss to preserve information within data views and an "agreement penalty" to encourage alignment across data views. By balancing the trade-off between these two key components in the objective, CoCA has the property of interpolating between the commonly-used principal component analysis (PCA) and canonical correlation analysis (CCA) as special cases at the two ends of the solution path. CoCA chooses the degree of agreement in a data-adaptive manner, using a validation set or cross-validation to estimate test error. Furthermore, we propose a sparse variant of CoCA that incorporates the Lasso penalty to yield feature sparsity, facilitating the identification of key features driving the observed patterns. We demonstrate the effectiveness of CoCA on simulated data and two real multiomics studies of COVID-19 and ductal carcinoma in situ of breast. In both real data applications, CoCA successfully integrates multiomics data, extracting components that are not only consistently present across different data views but also more informative and predictive of disease progression. CoCA offers a powerful framework for discovering important shared signals in multi-view data, with the potential to uncover novel insights in an increasingly multi-view data world.
We developed and validated an instrument to measure the perceived readability in data visualization: PREVis. Researchers and practitioners can easily use this instrument as part of their evaluations to compare the perceived readability of different visual data representations. Our instrument can complement results from controlled experiments on user task performance or provide additional data during in-depth qualitative work such as design iterations when developing a new technique. Although readability is recognized as an essential quality of data visualizations, so far there has not been a unified definition of the construct in the context of visual representations. As a result, researchers often lack guidance for determining how to ask people to rate their perceived readability of a visualization. To address this issue, we engaged in a rigorous process to develop the first validated instrument targeted at the subjective readability of visual data representations. Our final instrument consists of 11 items across 4 dimensions: understandability, layout clarity, readability of data values, and readability of data patterns. We provide the questionnaire as a document with implementation guidelines on osf.io/9cg8j. Beyond this instrument, we contribute a discussion of how researchers have previously assessed visualization readability, and an analysis of the factors underlying perceived readability in visual data representations.
Recent advances in Large Language Models (LLMs) have significantly shaped the applications of AI in multiple fields, including the studies of legal intelligence. Trained on extensive legal texts, including statutes and legal documents, the legal LLMs can capture important legal knowledge/concepts effectively and provide important support for downstream legal applications such as legal consultancy. Yet, the dynamic nature of legal statutes and interpretations also poses new challenges to the use of LLMs in legal applications. Particularly, how to update the legal knowledge of LLMs effectively and efficiently has become an important research problem in practice. Existing benchmarks for evaluating knowledge update methods are mostly designed for the open domain and cannot address the specific challenges of the legal domain, such as the nuanced application of new legal knowledge, the complexity and lengthiness of legal regulations, and the intricate nature of legal reasoning. To address this gap, we introduce the Legal Knowledge Update BEnchmark, i.e. LeKUBE, which evaluates knowledge update methods for legal LLMs across five dimensions. Specifically, we categorize the needs of knowledge updates in the legal domain with the help of legal professionals, and then hire annotators from law schools to create synthetic updates to the Chinese Criminal and Civil Code as well as sets of questions of which the answers would change after the updates. Through a comprehensive evaluation of state-of-the-art knowledge update methods, we reveal a notable gap between existing knowledge update methods and the unique needs of the legal domain, emphasizing the need for further research and development of knowledge update mechanisms tailored for legal LLMs.
Plane adjustment (PA) is crucial for many 3D applications, involving simultaneous pose estimation and plane recovery. Despite recent advancements, it remains a challenging problem in the realm of multi-view point cloud registration. Current state-of-the-art methods can achieve globally optimal convergence only with good initialization. Furthermore, their high time complexity renders them impractical for large-scale problems. To address these challenges, we first exploit a novel optimization strategy termed \textit{Bi-Convex Relaxation}, which decouples the original problem into two simpler sub-problems, reformulates each sub-problem using a convex relaxation technique, and alternately solves each one until the original problem converges. Building on this strategy, we propose two algorithmic variants for solving the plane adjustment problem, namely \textit{GlobalPointer} and \textit{GlobalPointer++}, based on point-to-plane and plane-to-plane errors, respectively. Extensive experiments on both synthetic and real datasets demonstrate that our method can perform large-scale plane adjustment with linear time complexity, larger convergence region, and robustness to poor initialization, while achieving similar accuracy as prior methods. The code is available at //github.com/wu-cvgl/GlobalPointer.
Graph convolutional networks (GCNs) have recently become one of the most powerful tools for graph analytics tasks in numerous applications, ranging from social networks and natural language processing to bioinformatics and chemoinformatics, thanks to their ability to capture the complex relationships between concepts. At present, the vast majority of GCNs use a neighborhood aggregation framework to learn a continuous and compact vector, then performing a pooling operation to generalize graph embedding for the classification task. These approaches have two disadvantages in the graph classification task: (1)when only the largest sub-graph structure ($k$-hop neighbor) is used for neighborhood aggregation, a large amount of early-stage information is lost during the graph convolution step; (2) simple average/sum pooling or max pooling utilized, which loses the characteristics of each node and the topology between nodes. In this paper, we propose a novel framework called, dual attention graph convolutional networks (DAGCN) to address these problems. DAGCN automatically learns the importance of neighbors at different hops using a novel attention graph convolution layer, and then employs a second attention component, a self-attention pooling layer, to generalize the graph representation from the various aspects of a matrix graph embedding. The dual attention network is trained in an end-to-end manner for the graph classification task. We compare our model with state-of-the-art graph kernels and other deep learning methods. The experimental results show that our framework not only outperforms other baselines but also achieves a better rate of convergence.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191