High Efficiency

High efficiency in various computational domains is a central research theme, aiming to minimize resource consumption (time, memory, energy) while maintaining or improving performance. Current efforts focus on developing novel algorithms and architectures, such as optimized Thompson sampling for reinforcement learning, sparse attention mechanisms for transformers, and efficient model compression techniques, to achieve this goal across diverse applications including natural language processing, computer vision, and robotics. These advancements are crucial for deploying complex AI models on resource-constrained devices and for accelerating scientific discovery in data-intensive fields.

Papers

February 22, 2022

February 21, 2022

On the Suitability of Neural Networks as Building Blocks for The Design of Efficient Learned Indexes
Domenico Amato, Giosue' Lo Bosco, Raffaele Giancarlo
Neural Network High Efficiency Data Structure Index Decomposition Learned Index Building Block Bloom Filter

February 17, 2022

Efficient and Reliable Probabilistic Interactive Learning with Structured Outputs
Stefano Teso, Antonio Vergari
High Efficiency Active Learning Probabilistic Model Structured Output Probabilistic Circuit Interactive Learning Output Space

February 7, 2022

Efficient Direct-Connect Topologies for Collective Communications
Liangyu Zhao, Siddharth Pal, Tapan Chugh, Weiyang Wang, Jason Fantl, Prithwish Basu, Joud Khoury, Arvind Krishnamurthy
High Efficiency Long Term Cooperation Network Topology Arbitrary Topology Collective Communication Optimal Topology

February 4, 2022

February 3, 2022

Efficient Autoprecoder-based deep learning for massive MU-MIMO Downlink under PA Non-Linearities
Xinying Cheng, Rafik Zayani, Marin Ferecatu, Nicolas Audebert
Deep Learning High Efficiency Massive MIMO Precoding Matrix

February 2, 2022

Integration of a machine learning model into a decision support tool to predict absenteeism at work of prospective employees
Gopal Nath, Antoine Harfouche, Austin Coursey, Krishna K. Saha, Srikanth Prabhu, Saptarshi Sengupta
Machine Learning Model High Efficiency Multinomial Logistic Decision Support Task Loss

January 28, 2022

January 23, 2022

Efficient and Robust Classification for Sparse Attacks
Mark Beliaev, Payam Delgosha, Hamed Hassani, Ramtin Pedarsani
High Efficiency Adversarial Training Defense Method Robust Classification Sparse Attack \Ell_1$ Norm

January 18, 2022

An Efficient Hashing-based Ensemble Method for Collaborative Outlier Detection
Kitty Li, Ninh Pham
High Efficiency Ensemble Method Locality Sensitive Hashing Local Detector Collaborative Anomaly Detection

January 15, 2022

Ensemble Transformer for Efficient and Accurate Ranking Tasks: an Application to Question Answering Systems
Yoshitomo Matsubara, Luca Soldaini, Eric Lind, Alessandro Moschitti
Application Proficiency High Efficiency Question Answering System Transformer Layer Large Transformer Model Model Distillation Ranking Consistency Large Scale Transformer Transformer Ensemble Heterogeneous Transformer

January 12, 2022

An Efficient and Adaptive Granular-ball Generation Method in Classification Problem
Shuyin Xia, Xiaochuan Dai, Guoyin Wang, Xinbo Gao, Elisabeth Giem
High Efficiency Classification Problem Granular Ball Granular Ball Generation

January 6, 2022

January 2, 2022

DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents
Kushagra Pandey, Avideep Mukherjee, Piyush Rai, Abhishek Kumar
High Efficiency Variational Autoencoders Diffusion Framework Low Dimensional Latent

December 29, 2021

An Efficient and Accurate Rough Set for Feature Selection, Classification and Knowledge Representation
Shuyin Xia, Xinyu Bai, Guoyin Wang, Deyu Meng, Xinbo Gao, Zizhong Chen, Elisabeth Giem
Classification Code High Efficiency Feature Selection Data Mining Knowledge Representation Rough Set

December 26, 2021

Efficient Diversity-Driven Ensemble for Deep Neural Networks
Wentao Zhang, Jiawei Jiang, Yingxia Shao, Bin Cui
Deep Neural Network High Efficiency Ensemble Learning Knowledge Transfer Diversity Regularizer Ensemble Accuracy

High Efficiency

Papers

Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet

Efficient and Differentiable Conformal Prediction with General Function Classes

On the Suitability of Neural Networks as Building Blocks for The Design of Efficient Learned Indexes

Efficient and Reliable Probabilistic Interactive Learning with Structured Outputs

Efficient Direct-Connect Topologies for Collective Communications

HENRI: High Efficiency Negotiation-based Robust Interface for Multi-party Multi-issue Negotiation over the Internet

Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realization

Efficient Autoprecoder-based deep learning for massive MU-MIMO Downlink under PA Non-Linearities

Integration of a machine learning model into a decision support tool to predict absenteeism at work of prospective employees

Benchmarking Resource Usage for Efficient Distributed Deep Learning

Efficient Embedding of Semantic Similarity in Control Policies via Entangled Bisimulation

Efficient and Robust Classification for Sparse Attacks

An Efficient Hashing-based Ensemble Method for Collaborative Outlier Detection

Ensemble Transformer for Efficient and Accurate Ranking Tasks: an Application to Question Answering Systems

An Efficient and Adaptive Granular-ball Generation Method in Classification Problem

PWM2Vec: An Efficient Embedding Approach for Viral Host Specification from Coronavirus Spike Sequences

Jointly Efficient and Optimal Algorithms for Logistic Bandits

DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents

An Efficient and Accurate Rough Set for Feature Selection, Classification and Knowledge Representation

Efficient Diversity-Driven Ensemble for Deep Neural Networks