Related papers: ScaleNet: Searching for the Model to Scale

This paper proposes an efficient neural network (NN) architecture design methodology called Chameleon that honors given resource constraints. Instead of developing new building blocks or using computationally-intensive reinforcement…

Gradient-based optimization has been critical to the success of machine learning, updating a single set of parameters to minimize a single loss. A growing number of applications rely on a generalization of this, where we have a bilevel or…

Grid superscheduling requires support for efficient and scalable discovery of resources. Resource discovery activities involve searching for the appropriate resource types that match the user's job requirements. To accomplish this goal, a…

With the rapid growth of fashion-focused social networks and online shopping, intelligent fashion recommendation is now in great need. We design algorithms which automatically suggest users outfits (e.g. a shirt, together with a skirt and a…

Scale-free networks are ubiquitous in social, biological and technological networked systems. Dynamic Scale-free networks and their synchronizations are important to understand and predict the behavior of social, biological and…

Existing learning-based surface reconstruction methods from point clouds are still facing challenges in terms of scalability and preservation of details on large-scale point clouds. In this paper, we propose the SSRNet, a novel scalable…

Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…

The generation and collection of big data series are becoming an integral part of many emerging applications in sciences, IoT, finance, and web applications among several others. The terabyte-scale of data series has motivated recent…

Deep neural networks (DNNs) have successfully been applied in many fields in the past decades. However, the increasing number of multiply-and-accumulate (MAC) operations in DNNs prevents their application in resource-constrained and…

A widely used paradigm to improve the generalization performance of high-capacity neural models is through the addition of auxiliary unsupervised tasks during supervised training. Tasks such as similarity matching and input reconstruction…

Federated learning (FL) is a recently developed area of machine learning, in which the private data of a large number of distributed clients is used to develop a global model under the coordination of a central server without explicitly…

In neural networks, the property of being equivariant to transformations improves generalization when the corresponding symmetry is present in the data. In particular, scale-equivariant networks are suited to computer vision tasks where the…

Neural Architecture Search (NAS), together with model scaling, has shown remarkable progress in designing high accuracy and fast convolutional architecture families. However, as neither NAS nor model scaling considers sufficient hardware…

Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…

The brute-force scaleup of training datasets, learnable parameters and computation power, has become a prevalent strategy for developing more robust learning models. However, due to bottlenecks in data, computation, and trust, the…

Subsequence-based time series classification algorithms provide accurate and interpretable models, but training these models is extremely computation intensive. The asymptotic time complexity of subsequence-based algorithms remains a…

In this paper, we propose a Classification Confidence Network (CLCNet) that can determine whether the classification model classifies input samples correctly. It can take a classification result in the form of vector in any dimension, and…

Many static benchmarks are beginning to saturate: as models rapidly improve, they achieve near-perfect scores on fixed test sets, leaving little headroom to expose genuine model weaknesses -- and even expert-curated challenge sets quickly…

Measurement is a fundamental building block of numerous scientific models and their creation. This is in particular true for data driven science. Due to the high complexity and size of modern data sets, the necessity for the development of…

Performance of standard processes over large distributed networks typically scales with the size of the network. For example, in planar topologies where nodes communicate with their natural neighbors, the scaling factor is $O(n)$, where $n$…