Benchmarking involves designing scientific test methods, tools, and frameworks to quantitatively and comparably assess specific performance indicators of certain test subjects. With the development of artificial intelligence, AI benchmarking datasets such as ImageNet and DataPerf have gradually become consensus standards in both academic and industrial fields. However, constructing a benchmarking framework remains a significant challenge in the open-source domain due to the diverse range of data types, the wide array of research issues, and the intricate nature of collaboration networks. This paper introduces OpenPerf, a benchmarking framework designed for the sustainable development of the open-source ecosystem. This framework defines 9 task benchmarking tasks in the open-source research, encompassing 3 data types: time series, text, and graphics, and addresses 6 research problems including regression, classification, recommendation, ranking, network building, and anomaly detection. Based on the above tasks, we implemented 3 data science task benchmarks, 2 index-based benchmarks, and 1 standard benchmark. Notably, the index-based benchmarks have been adopted by the China Electronics Standardization Institute as evaluation criteria for open-source community governance. Additionally, we have developed a comprehensive toolkit for OpenPerf, which not only offers robust data management, tool integration, and user interface capabilities but also adopts a Benchmarking-as-a-Service (BaaS) model to serve academic institutions, industries, and foundations. Through its application in renowned companies and institutions such as Alibaba, Ant Group, and East China Normal University, we have validated OpenPerf's pivotal role in the healthy evolution of the open-source ecosystem.
相關內容
Leveraging recent advancements in large language models, modern neural code completion models have demonstrated the capability to generate highly accurate code suggestions. However, their massive size poses challenges in terms of computational costs and environmental impact, hindering their widespread adoption in practical scenarios. Dynamic inference emerges as a promising solution, as it allocates minimal computation during inference while maintaining the model's performance. In this research, we explore dynamic inference within the context of code completion. Initially, we conducted an empirical investigation on GPT-2, focusing on the inference capabilities of intermediate layers for code completion. We found that 54.4% of tokens can be accurately generated using just the first layer, signifying significant computational savings potential. Moreover, despite using all layers, the model still fails to predict 14.5% of tokens correctly, and the subsequent completions continued from them are rarely considered helpful, with only a 4.2% Acceptance Rate. These findings motivate our exploration of dynamic inference in code completion and inspire us to enhance it with a decision-making mechanism that stops the generation of incorrect code. We thus propose a novel dynamic inference method specifically tailored for code completion models. This method aims not only to produce correct predictions with largely reduced computation but also to prevent incorrect predictions proactively. Our extensive evaluation shows that it can averagely skip 1.7 layers out of 16 layers in the models, leading to an 11.2% speedup with only a marginal 1.1% reduction in ROUGE-L.
Data attribution methods trace model behavior back to its training dataset, offering an effective approach to better understand ``black-box'' neural networks. While prior research has established quantifiable links between model output and training data in diverse settings, interpreting diffusion model outputs in relation to training samples remains underexplored. In particular, diffusion models operate over a sequence of timesteps instead of instantaneous input-output relationships in previous contexts, posing a significant challenge to extend existing frameworks to diffusion models directly. Notably, we present Diffusion-TracIn that incorporates this temporal dynamics and observe that samples' loss gradient norms are highly dependent on timestep. This trend leads to a prominent bias in influence estimation, and is particularly noticeable for samples trained on large-norm-inducing timesteps, causing them to be generally influential. To mitigate this effect, we introduce Diffusion-ReTrac as a re-normalized adaptation that enables the retrieval of training samples more targeted to the test sample of interest, facilitating a localized measurement of influence and considerably more intuitive visualization. We demonstrate the efficacy of our approach through various evaluation metrics and auxiliary tasks, reducing the amount of generally influential samples to $\frac{1}{3}$ of its original quantity.
Software engineering (SE) requires developers to collaborate with stakeholders, and understanding their emotions and perspectives is often vital. Empathy is a concept characterising a person's ability to understand and share the feelings of another. However, empathy continues to be an under-researched human aspect in SE. We studied how empathy is practised between developers and end users using a mixed methods case study. We used an empathy test, observations and interviews to collect data, and socio technical grounded theory and descriptive statistics to analyse data. We identified the nature of awareness required to trigger empathy and enablers of empathy. We discovered barriers to empathy and a set of potential strategies to overcome these barriers. We report insights on emerging relationships and present a set of recommendations and potential future works on empathy and SE for software practitioners and SE researchers.
We present a comprehensive, user-centric approach to understand preferences in AI-based productivity agents and develop personalized solutions tailored to users' needs. Utilizing a two-phase method, we first conducted a survey with 363 participants, exploring various aspects of productivity, communication style, agent approach, personality traits, personalization, and privacy. Drawing on the survey insights, we developed a GPT-4 powered personalized productivity agent that utilizes telemetry data gathered via Viva Insights from information workers to provide tailored assistance. We compared its performance with alternative productivity-assistive tools, such as dashboard and narrative, in a study involving 40 participants. Our findings highlight the importance of user-centric design, adaptability, and the balance between personalization and privacy in AI-assisted productivity tools. By building on the insights distilled from our study, we believe that our work can enable and guide future research to further enhance productivity solutions, ultimately leading to optimized efficiency and user experiences for information workers.
Large language models' (LLMs) abilities are drawn from their pretraining data, and model development begins with data curation. However, decisions around what data is retained or removed during this initial stage is under-scrutinized. In our work, we ground web text, which is a popular pretraining data source, to its social and geographic contexts. We create a new dataset of 10.3 million self-descriptions of website creators, and extract information about who they are and where they are from: their topical interests, social roles, and geographic affiliations. Then, we conduct the first study investigating how ten "quality" and English language identification (langID) filters affect webpages that vary along these social dimensions. Our experiments illuminate a range of implicit preferences in data curation: we show that some quality classifiers act like topical domain filters, and langID can overlook English content from some regions of the world. Overall, we hope that our work will encourage a new line of research on pretraining data curation practices and its social implications.
Beyond 5G and 6G networks are expected to support new and challenging use cases and applications that depend on a certain level of Quality of Service (QoS) to operate smoothly. Predicting the QoS in a timely manner is of high importance, especially for safety-critical applications as in the case of vehicular communications. Although until recent years the QoS prediction has been carried out by centralized Artificial Intelligence (AI) solutions, a number of privacy, computational, and operational concerns have emerged. Alternative solutions have been surfaced (e.g. Split Learning, Federated Learning), distributing AI tasks of reduced complexity across nodes, while preserving the privacy of the data. However, new challenges rise when it comes to scalable distributed learning approaches, taking into account the heterogeneous nature of future wireless networks. The current work proposes DISTINQT, a privacy-aware distributed learning framework for QoS prediction. Our framework supports multiple heterogeneous nodes, in terms of data types and model architectures, by sharing computations across them. This, enables the incorporation of diverse knowledge into a sole learning process that will enhance the robustness and generalization capabilities of the final QoS prediction model. DISTINQT also contributes to data privacy preservation by encoding any raw input data into a non-linear latent representation before any transmission. Evaluation results showcase that our framework achieves a statistically identical performance compared to its centralized version and an average performance improvement of up to 65% against six state-of-the-art centralized baseline solutions in the Tele-Operated Driving use case.
Autonomic computing investigates how systems can achieve (user) specified control outcomes on their own, without the intervention of a human operator. Autonomic computing fundamentals have been substantially influenced by those of control theory for closed and open-loop systems. In practice, complex systems may exhibit a number of concurrent and inter-dependent control loops. Despite research into autonomic models for managing computer resources, ranging from individual resources (e.g., web servers) to a resource ensemble (e.g., multiple resources within a data center), research into integrating Artificial Intelligence (AI) and Machine Learning (ML) to improve resource autonomy and performance at scale continues to be a fundamental challenge. The integration of AI/ML to achieve such autonomic and self-management of systems can be achieved at different levels of granularity, from full to human-in-the-loop automation. In this article, leading academics, researchers, practitioners, engineers, and scientists in the fields of cloud computing, AI/ML, and quantum computing join to discuss current research and potential future directions for these fields. Further, we discuss challenges and opportunities for leveraging AI and ML in next generation computing for emerging computing paradigms, including cloud, fog, edge, serverless and quantum computing environments.
Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference. We study the impact of model size in this setting, focusing on Transformer models for NLP tasks that are limited by compute: self-supervised pretraining and high-resource machine translation. We first show that even though smaller Transformer models execute faster per iteration, wider and deeper models converge in significantly fewer steps. Moreover, this acceleration in convergence typically outpaces the additional computational overhead of using larger models. Therefore, the most compute-efficient training strategy is to counterintuitively train extremely large models but stop after a small number of iterations. This leads to an apparent trade-off between the training efficiency of large Transformer models and the inference efficiency of small Transformer models. However, we show that large models are more robust to compression techniques such as quantization and pruning than small models. Consequently, one can get the best of both worlds: heavily compressed, large models achieve higher accuracy than lightly compressed, small models.
We introduce a multi-task setup of identifying and classifying entities, relations, and coreference clusters in scientific articles. We create SciERC, a dataset that includes annotations for all three tasks and develop a unified framework called Scientific Information Extractor (SciIE) for with shared span representations. The multi-task setup reduces cascading errors between tasks and leverages cross-sentence relations through coreference links. Experiments show that our multi-task model outperforms previous models in scientific information extraction without using any domain-specific features. We further show that the framework supports construction of a scientific knowledge graph, which we use to analyze information in scientific literature.
In order to answer natural language questions over knowledge graphs, most processing pipelines involve entity and relation linking. Traditionally, entity linking and relation linking has been performed either as dependent sequential tasks or independent parallel tasks. In this paper, we propose a framework called "EARL", which performs entity linking and relation linking as a joint single task. EARL uses a graph connection based solution to the problem. We model the linking task as an instance of the Generalised Travelling Salesman Problem (GTSP) and use GTSP approximate algorithm solutions. We later develop EARL which uses a pair-wise graph-distance based solution to the problem.The system determines the best semantic connection between all keywords of the question by referring to a knowledge graph. This is achieved by exploiting the "connection density" between entity candidates and relation candidates. The "connection density" based solution performs at par with the approximate GTSP solution.We have empirically evaluated the framework on a dataset with 5000 questions. Our system surpasses state-of-the-art scores for entity linking task by reporting an accuracy of 0.65 to 0.40 from the next best entity linker.
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