English
Related papers

Related papers: ScaleNet: Searching for the Model to Scale

200 papers

Pattern matching is a fundamental tool for answering complex graph queries. Unfortunately, existing solutions have limited capabilities: they do not scale to process large graphs and/or support only a restricted set of search templates or…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-09-22 Tahsin Reza , Hassan Halawa , Matei Ripeanu , Geoffrey Sanders , Roger Pearce

It is by now a well known fact in the graph learning community that the presence of bottlenecks severely limits the ability of graph neural networks to propagate information over long distances. What so far has not been appreciated is that,…

Machine Learning · Computer Science 2023-10-31 Christian Koke , Abhishek Saroha , Yuesong Shen , Marvin Eisenberger , Daniel Cremers

In this paper we present an approach for training deep generative models solely based on solving determined systems of linear equations. A network that uses this approach, called a StarNet, has the following desirable properties: 1)…

Machine Learning · Computer Science 2021-01-08 Amir Zadeh , Santiago Benoit , Louis-Philippe Morency

Test-time compute scaling has emerged as a powerful paradigm for enhancing mathematical reasoning in large language models (LLMs) by allocating additional computational resources during inference. However, current methods employ uniform…

Computation and Language · Computer Science 2025-12-02 Yang Xiao , Chunpu Xu , Ruifeng Yuan , Jiashuo Wang , Wenjie Li , Pengfei Liu

In this paper, we propose SwarmNet -- a neural network architecture that can learn to predict and imitate the behavior of an observed swarm of agents in a centralized manner. Tested on artificially generated swarm motion data, the network…

Neural and Evolutionary Computing · Computer Science 2020-11-04 Siyu Zhou , Mariano Phielipp , Jorge A. Sefair , Sara I. Walker , Heni Ben Amor

Identifying critical nodes and links in graphs is a crucial task. These nodes/links typically represent critical elements/communication links that play a key role in a system's performance. However, a majority of the methods available in…

Social and Information Networks · Computer Science 2022-05-31 Sai Munikoti , Laya Das , Balasubramaniam Natarajan

Most deep learning backbones are evaluated on ImageNet. Using scenery images as an example, we conducted extensive experiments to demonstrate the widely accepted principles in network design may result in dramatic performance differences…

Computer Vision and Pattern Recognition · Computer Science 2023-03-15 Zhinan Qiao , Xiaohui Yuan

Recent advances in Neural Architecture Search (NAS) such as one-shot NAS offer the ability to extract specialized hardware-aware sub-network configurations from a task-specific super-network. While considerable effort has been employed…

Machine Learning · Computer Science 2022-05-24 Daniel Cummings , Anthony Sarah , Sharath Nittur Sridhar , Maciej Szankin , Juan Pablo Munoz , Sairam Sundaresan

Offsite-tuning is a privacy-preserving method for tuning large language models (LLMs) by sharing a lossy compressed emulator from the LLM owners with data owners for downstream task tuning. This approach protects the privacy of both the…

Computation and Language · Computer Science 2024-12-16 Kai Yao , Zhaorui Tan , Tiandi Ye , Lichun Li , Yuan Zhao , Wenyan Liu , Wei Wang , Jianke Zhu

The algorithms of one-shot neural architecture search(NAS) have been widely used to reduce computation consumption. However, because of the interference among the subnets in which weights are shared, the subnets inherited from these…

Computer Vision and Pattern Recognition · Computer Science 2022-06-15 Jiawei Liu , Kaiyu Zhang , Weitai Hu , Qing Yang

The rapid scaling of large language model training requires distributing GPU resources across multiple data center buildings and regions. We refer to such paradigm as "scale-across" training. As infrastructure expands, the system design…

Scaling deep learning models has been at the heart of recent revolutions in language modelling and image generation. Practitioners have observed a strong relationship between model size, dataset size, and performance. However,…

While deeper convolutional networks are needed to achieve maximum accuracy in visual perception tasks, for many inputs shallower networks are sufficient. We exploit this observation by learning to skip convolutional layers on a per-input…

Computer Vision and Pattern Recognition · Computer Science 2018-07-26 Xin Wang , Fisher Yu , Zi-Yi Dou , Trevor Darrell , Joseph E. Gonzalez

Serverless computing has emerged as a promising computing paradigm for edge computing. However, adopting the event driven model in highly dynamic, heterogeneous, and distributed edge systems poses significant challenges in request placement…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-18 Chen Chen , Zihan Jia , Andrea Sabbioni , Reza Farahani , Lei Jiao

Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents…

Neural Architecture Search (NAS) has demonstrated its efficacy in computer vision and potential for ranking systems. However, prior work focused on academic problems, which are evaluated at small scale under well-controlled fixed baselines.…

Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency.…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Mingxing Tan , Ruoming Pang , Quoc V. Le

Graph representation learning has recently been applied to a broad spectrum of problems ranging from computer graphics and chemistry to high energy physics and social media. The popularity of graph neural networks has sparked interest, both…

Machine Learning · Computer Science 2020-11-05 Fabrizio Frasca , Emanuele Rossi , Davide Eynard , Ben Chamberlain , Michael Bronstein , Federico Monti

We propose a scalable framework for the learning of high-dimensional parametric maps via adaptively constructed residual network (ResNet) maps between reduced bases of the inputs and outputs. When just few training data are available, it is…

Skill routing is an important component in large-scale conversational systems. In contrast to traditional rule-based skill routing, state-of-the-art systems use a model-based approach to enable natural conversations. To provide supervision…

Machine Learning · Computer Science 2022-04-15 Mohammad Kachuee , Jinseok Nam , Sarthak Ahuja , Jin-Myung Won , Sungjin Lee