Search Results for author:
Found 16 papers, 4 papers with code
Layout-Aware Text Representations Harm Clustering Documents by Type
Clustering documents by type—grouping invoices with invoices and articles with articles—is a desirable first step for organizing large collections of document scans.
ProtoNER: Few shot Incremental Learning for Named Entity Recognition using Prototypical Networks
\\ We present \textbf{ProtoNER}: Prototypical Network based end-to-end KVP extraction model that allows addition of new classes to an existing model while requiring minimal number of newly annotated training samples.
FLIPS: Federated Learning using Intelligent Participant Selection
In particular, we examine the benefits of label distribution clustering on participant selection in federated learning.
GVdoc: Graph-based Visual Document Classification
Visual document classifiers have shown impressive performance on in-distribution test sets.
Position Masking for Improved Layout-Aware Document Understanding
Natural language processing for document scans and PDFs has the potential to enormously improve the efficiency of business processes.
Separation of Powers in Federated Learning
In this paper, we introduce TRUDA, a new cross-silo FL system, employing a trustworthy and decentralized aggregation architecture to break down information concentration with regard to a single aggregator.
Adversarial training in communication constrained federated learning
We observe a significant drop in both natural and adversarial accuracies when AT is used in the federated setting as opposed to centralized training.
MYSTIKO : : Cloud-Mediated, Private, Federated Gradient Descent
Federated learning enables multiple, distributed participants (potentially on different clouds) to collaborate and train machine/deep learning models by sharing parameters/gradients.
IBM Federated Learning: an Enterprise Framework White Paper V0.1
Federated Learning (FL) is an approach to conduct machine learning without centralizing training data in a single place, for reasons of privacy, confidentiality or data volume.
Effective Elastic Scaling of Deep Learning Workloads
We design a fast dynamic programming based optimizer to solve this problem in real-time to determine jobs that can be scaled up/down, and use this optimizer in an autoscaler to dynamically change the allocated resources and batch sizes of individual DL jobs.
Improving the affordability of robustness training for DNNs
Projected Gradient Descent (PGD) based adversarial training has become one of the most prominent methods for building robust deep neural network models.
PoWER-BERT: Accelerating BERT Inference via Progressive Word-vector Elimination
We demonstrate that our method attains up to 6. 8x reduction in inference time with <1% loss in accuracy when applied over ALBERT, a highly compressed version of BERT.
A Simple Dynamic Learning Rate Tuning Algorithm For Automated Training of DNNs
Training neural networks on image datasets generally require extensive experimentation to find the optimal learning rate regime.
Compression of Deep Neural Networks by combining pruning and low rank decomposition
Large number of weights in deep neural networks make the models difficult to be deployed in low memory environments such as, mobile phones, IOT edge devices as well as "inferencing as a service" environments on the cloud.
Automatic Assessment of Artistic Quality of Photos
The dataset contains some images captured by professional photographers and the rest of the images captured by common people.
Efficient Inferencing of Compressed Deep Neural Networks
Large number of weights in deep neural networks makes the models difficult to be deployed in low memory environments such as, mobile phones, IOT edge devices as well as "inferencing as a service" environments on cloud.
