The growing concern for energy efficiency in the Information and Communication Technology (ICT) sector has prompted the exploration of resource management techniques. While hardware architectures, such as single-ISA asymmetric multicore processors (AMP), offer potential energy savings, there is still untapped potential for software optimizations. This paper aims to bridge this gap by investigating the scheduling of garbage collection (GC) activities on a heterogeneous architecture with both performance cores ("p-cores") and energy cores ("e-cores") to achieve energy savings. Our study focuses on the concurrent ZGC collector in the context of Java Virtual Machines (JVM), as the energy aspect is not well studied in the context of latency-sensitive Java workloads. By comparing the energy efficiency, performance, latency, and memory utilization of executing GC on p-cores versus e-cores, we present compelling findings. We demonstrate that scheduling GC work on e-cores overall leads to approximately 3% energy savings without performance and mean latency degradation while requiring no additional effort from developers. Overall energy reduction can increase to 5.3$\pm$0.0225% by tuning the number of e-cores (still not changing the program!). Our findings highlight the practicality and benefits of scheduling GC on e-cores, showcasing the potential for energy savings in heterogeneous architectures running Java workloads while meeting critical latency requirements. Our research contributes to the ongoing efforts toward achieving a more sustainable and efficient ICT sector.
相關內容
Previous work in Neural Loss Function Search (NLFS) has shown a lack of correlation between smaller surrogate functions and large convolutional neural networks with massive regularization. We expand upon this research by revealing another disparity that exists, correlation between different types of image augmentation techniques. We show that different loss functions can perform well on certain image augmentation techniques, while performing poorly on others. We exploit this disparity by performing an evolutionary search on five types of image augmentation techniques in the hopes of finding image augmentation specific loss functions. The best loss functions from each evolution were then taken and transferred to WideResNet-28-10 on CIFAR-10 and CIFAR-100 across each of the five image augmentation techniques. The best from that were then taken and evaluated by fine-tuning EfficientNetV2Small on the CARS, Oxford-Flowers, and Caltech datasets across each of the five image augmentation techniques. Multiple loss functions were found that outperformed cross-entropy across multiple experiments. In the end, we found a single loss function, which we called the inverse bessel logarithm loss, that was able to outperform cross-entropy across the majority of experiments.
Byzantine agreement allows n processes to decide on a common value, in spite of arbitrary failures. The seminal Dolev-Reischuk bound states that any deterministic solution to Byzantine agreement exchanges Omega(n^2) bits. In synchronous networks, solutions with optimal O(n^2) bit complexity, optimal fault tolerance, and no cryptography have been established for over three decades. However, these solutions lack robustness under adverse network conditions. Therefore, research has increasingly focused on Byzantine agreement for partially synchronous networks. Numerous solutions have been proposed for the partially synchronous setting. However, these solutions are notoriously hard to prove correct, and the most efficient cryptography-free algorithms still require O(n^3) exchanged bits in the worst case. In this paper, we introduce Oper, the first generic transformation of deterministic Byzantine agreement algorithms from synchrony to partial synchrony. Oper requires no cryptography, is optimally resilient (n >= 3t+1, where t is the maximum number of failures), and preserves the worst-case per-process bit complexity of the transformed synchronous algorithm. Leveraging Oper, we present the first partially synchronous Byzantine agreement algorithm that (1) achieves optimal O(n^2) bit complexity, (2) requires no cryptography, and (3) is optimally resilient (n >= 3t+1), thus showing that the Dolev-Reischuk bound is tight even in partial synchrony. Moreover, we adapt Oper for long values and obtain several new partially synchronous algorithms with improved complexity and weaker (or completely absent) cryptographic assumptions.
Sentence Embedding stands as a fundamental task within the realm of Natural Language Processing, finding extensive application in search engines, expert systems, and question-and-answer platforms. With the continuous evolution of large language models such as LLaMA and Mistral, research on sentence embedding has recently achieved notable breakthroughs. However, these advancements mainly pertain to fine-tuning scenarios, leaving explorations into computationally efficient direct inference methods for sentence representation in a nascent stage. This paper endeavors to bridge this research gap. Through comprehensive experimentation, we challenge the widely held belief in the necessity of an Explicit One-word Limitation for deriving sentence embeddings from Pre-trained Language Models (PLMs). We demonstrate that this approach, while beneficial for generative models under direct inference scenario, is not imperative for discriminative models or the fine-tuning of generative PLMs. This discovery sheds new light on the design of manual templates in future studies. Building upon this insight, we propose two innovative prompt engineering techniques capable of further enhancing the expressive power of PLMs' raw embeddings: Pretended Chain of Thought and Knowledge Enhancement. We confirm their effectiveness across various PLM types and provide a detailed exploration of the underlying factors contributing to their success.
The energy market encompasses the behavior of energy supply and trading within a platform system. By utilizing centralized or distributed trading, energy can be effectively managed and distributed across different regions, thereby achieving market equilibrium and satisfying both producers and consumers. However, recent years have presented unprecedented challenges and difficulties for the development of the energy market. These challenges include regional energy imbalances, volatile energy pricing, high computing costs, and issues related to transaction information disclosure. Researchers widely acknowledge that the security features of blockchain technology can enhance the efficiency of energy transactions and establish the fundamental stability and robustness of the energy market. This type of blockchain-enabled energy market is commonly referred to as an energy blockchain. Currently, there is a burgeoning amount of research in this field, encompassing algorithm design, framework construction, and practical application. It is crucial to organize and compare these research efforts to facilitate the further advancement of energy blockchain. This survey aims to comprehensively review the fundamental characteristics of blockchain and energy markets, highlighting the significant advantages of combining the two. Moreover, based on existing research outcomes, we will categorize and compare the current energy market research supported by blockchain in terms of algorithm design, market framework construction, and the policies and practical applications adopted by different countries. Finally, we will address current issues and propose potential future directions for improvement, to provide guidance for the practical implementation of blockchain in the energy market.
Recent observations have underscored a disparity between the inflated benchmark scores and the actual performance of LLMs, raising concerns about potential contamination of evaluation benchmarks. This issue is especially critical for closed-source models and certain open-source models where training data transparency is lacking. In this paper we study data contamination by proposing two methods tailored for both open-source and proprietary LLMs. We first introduce a retrieval-based system to explore potential overlaps between evaluation benchmarks and pretraining corpora. We further present a novel investigation protocol named \textbf{T}estset \textbf{S}lot Guessing (\textit{TS-Guessing}), applicable to both open and proprietary models. This approach entails masking a wrong answer in a multiple-choice question and prompting the model to fill in the gap. Additionally, it involves obscuring an unlikely word in an evaluation example and asking the model to produce it. We find that certain commercial LLMs could surprisingly guess the missing option in various test sets. Specifically, in the TruthfulQA benchmark, we find that LLMs exhibit notable performance improvement when provided with additional metadata in the benchmark. Further, in the MMLU benchmark, ChatGPT and GPT-4 demonstrated an exact match rate of 52\% and 57\%, respectively, in guessing the missing options in benchmark test data. We hope these results underscore the need for more robust evaluation methodologies and benchmarks in the field.
To meet the urgent requirements for the climate change mitigation, several proactive measures of energy efficiency have been implemented in maritime industry. Many of these practices depend highly on the onboard data of vessel's operation and environmental conditions. In this paper, a high resolution onboard data from passenger vessels in short-sea shipping (SSS) have been collected and preprocessed. We first investigated the available data to deploy it effectively to model the physics of the vessel, and hence the vessel performance. Since in SSS, the weather measurements and forecasts might have not been in temporal and spatial resolutions that accurately representing the actual environmental conditions. Then, We proposed a data-driven modeling approach for vessel energy efficiency. This approach addresses the challenges of data representation and energy modeling by combining and aggregating data from multiple sources and seamlessly integrates explainable artificial intelligence (XAI) to attain clear insights about the energy efficiency for a vessel in SSS. After that, the developed model of energy efficiency has been utilized in developing a framework for optimizing the vessel voyage to minimize the fuel consumption and meeting the constraint of arrival time. Moreover, we developed a spatial clustering approach for labeling the vessel paths to detect the paths for vessels with operating routes of repeatable and semi-repeatable paths.
Non-negative matrix factorization (NMF) is a dimensionality reduction technique that has shown promise for analyzing noisy data, especially astronomical data. For these datasets, the observed data may contain negative values due to noise even when the true underlying physical signal is strictly positive. Prior NMF work has not treated negative data in a statistically consistent manner, which becomes problematic for low signal-to-noise data with many negative values. In this paper we present two algorithms, Shift-NMF and Nearly-NMF, that can handle both the noisiness of the input data and also any introduced negativity. Both of these algorithms use the negative data space without clipping, and correctly recover non-negative signals without any introduced positive offset that occurs when clipping negative data. We demonstrate this numerically on both simple and more realistic examples, and prove that both algorithms have monotonically decreasing update rules.
Large Language Models (LLMs) have emerged as powerful tools in the field of Natural Language Processing (NLP) and have recently gained significant attention in the domain of Recommendation Systems (RS). These models, trained on massive amounts of data using self-supervised learning, have demonstrated remarkable success in learning universal representations and have the potential to enhance various aspects of recommendation systems by some effective transfer techniques such as fine-tuning and prompt tuning, and so on. The crucial aspect of harnessing the power of language models in enhancing recommendation quality is the utilization of their high-quality representations of textual features and their extensive coverage of external knowledge to establish correlations between items and users. To provide a comprehensive understanding of the existing LLM-based recommendation systems, this survey presents a taxonomy that categorizes these models into two major paradigms, respectively Discriminative LLM for Recommendation (DLLM4Rec) and Generative LLM for Recommendation (GLLM4Rec), with the latter being systematically sorted out for the first time. Furthermore, we systematically review and analyze existing LLM-based recommendation systems within each paradigm, providing insights into their methodologies, techniques, and performance. Additionally, we identify key challenges and several valuable findings to provide researchers and practitioners with inspiration.
Graph Neural Networks (GNNs) have recently become increasingly popular due to their ability to learn complex systems of relations or interactions arising in a broad spectrum of problems ranging from biology and particle physics to social networks and recommendation systems. Despite the plethora of different models for deep learning on graphs, few approaches have been proposed thus far for dealing with graphs that present some sort of dynamic nature (e.g. evolving features or connectivity over time). In this paper, we present Temporal Graph Networks (TGNs), a generic, efficient framework for deep learning on dynamic graphs represented as sequences of timed events. Thanks to a novel combination of memory modules and graph-based operators, TGNs are able to significantly outperform previous approaches being at the same time more computationally efficient. We furthermore show that several previous models for learning on dynamic graphs can be cast as specific instances of our framework. We perform a detailed ablation study of different components of our framework and devise the best configuration that achieves state-of-the-art performance on several transductive and inductive prediction tasks for dynamic graphs.
Named entity recognition (NER) is the task to identify text spans that mention named entities, and to classify them into predefined categories such as person, location, organization etc. NER serves as the basis for a variety of natural language applications such as question answering, text summarization, and machine translation. Although early NER systems are successful in producing decent recognition accuracy, they often require much human effort in carefully designing rules or features. In recent years, deep learning, empowered by continuous real-valued vector representations and semantic composition through nonlinear processing, has been employed in NER systems, yielding stat-of-the-art performance. In this paper, we provide a comprehensive review on existing deep learning techniques for NER. We first introduce NER resources, including tagged NER corpora and off-the-shelf NER tools. Then, we systematically categorize existing works based on a taxonomy along three axes: distributed representations for input, context encoder, and tag decoder. Next, we survey the most representative methods for recent applied techniques of deep learning in new NER problem settings and applications. Finally, we present readers with the challenges faced by NER systems and outline future directions in this area.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191