Efficient Alternative

Research into efficient alternatives focuses on developing faster and more resource-friendly methods for various machine learning tasks, addressing the limitations of computationally expensive models. Current efforts concentrate on developing scalable graph neural networks, improving molecular fingerprint generation techniques, and exploring ensemble methods and alternative architectures that match or exceed the performance of larger, more complex models in natural language processing, reinforcement learning, and image classification. These advancements are significant because they enable the application of powerful machine learning techniques to larger datasets and more complex problems while reducing computational costs and energy consumption.

Papers

November 7, 2024

The Fibonacci Network: A Simple Alternative for Positional Encoding
Yair Bleiberg, Michael Werman
Batch Normalization Multi Layer Perceptron Coordinate Based Efficient Alternative Recurrence Network

June 17, 2024

A Scalable and Effective Alternative to Graph Transformers
Kaan Sancak, Zhigang Hua, Jin Fang, Yan Xie, Andrey Malevich, Bo Long, Muhammed Fatih Balin, Ümit V. Çatalyürek
Graph Neural Network Graph Representation Learning Graph Transformer Large Scale Graph Global Convolution Efficient Alternative

March 10, 2024

Sort & Slice: A Simple and Superior Alternative to Hash-Based Folding for Extended-Connectivity Fingerprints
Markus Dablander, Thierry Hanser, Renaud Lambiotte, Garrett M. Morris
Machine Learning Molecular Property Prediction Auxiliary Sorting Network Rearranges Cheminformatics Task Chemical Property Prediction Slice by Slice Molecular Image Efficient Alternative

January 4, 2024

Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM
Xiaoding Lu, Zongyi Liu, Adian Liusie, Vyas Raina, Vineet Mudupalli, Yuwen Zhang, William Beauchamp
Billion Parameter Blending Method Efficient Alternative Computational Demand

May 29, 2023

VA-learning as a more efficient alternative to Q-learning
Yunhao Tang, Rémi Munos, Mark Rowland, Michal Valko
Reinforcement Learning Q Learning Q Function Efficient Alternative

May 24, 2023

Revisiting Parallel Context Windows: A Frustratingly Simple Alternative and Chain-of-Thought Deterioration
Kejuan Yang, Xiao Liu, Kaiwen Men, Aohan Zeng, Yuxiao Dong, Jie Tang
Language Model Long Context Context Length Shot in Context Learning Context Window Document Degradation Efficient Alternative

January 30, 2023

Can Persistent Homology provide an efficient alternative for Evaluation of Knowledge Graph Completion Methods?
Anson Bastos, Kuldeep Singh, Abhishek Nadgeri, Johannes Hoffart, Toyotaro Suzumura, Manish Singh
Knowledge Graph Global Evaluation Knowledge Graph Completion Topological Data Analysis Persistent Homology Efficient Alternative

October 10, 2022

Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling
Haw-Shiuan Chang, Ruei-Yao Sun, Kathryn Ricci, Andrew McCallum
BERT Model Model Ensembling Efficient Alternative Ensemble BERT

October 6, 2022

Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery
Felix Chalumeau, Raphael Boige, Bryan Lim, Valentin Macé, Maxime Allard, Arthur Flajolet, Antoine Cully, Thomas Pierrot
Reinforcement Learning Deep Reinforcement Learning Hierarchical Planning Skill Discovery Efficient Alternative NeuroEvolution Method

September 16, 2022

Top-Tuning: a study on transfer learning for an efficient alternative to fine tuning for image classification with fast kernel methods
Paolo Didier Alfano, Vito Paolo Pastore, Lorenzo Rosasco, Francesca Odone
Fine Tuning Transfer Learning Image Classification Pre Trained Convolutional Neural Network Efficient Alternative Fast Kernel Recyclable Tuning

June 23, 2022

Rethinking Collaborative Metric Learning: Toward an Efficient Alternative without Negative Sampling
Shilong Bao, Qianqian Xu, Zhiyong Yang, Xiaochun Cao, Qingming Huang
Negative Sampling Efficient Alternative Collaborative Metric Learning

January 26, 2022

When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism
Guangting Wang, Yucheng Zhao, Chuanxin Tang, Chong Luo, Wenjun Zeng
Vision Transformer Attention Mechanism Swin Transformer Attention Layer Two Shift Efficient Alternative

Efficient Alternative

Papers

The Fibonacci Network: A Simple Alternative for Positional Encoding

A Scalable and Effective Alternative to Graph Transformers

Sort & Slice: A Simple and Superior Alternative to Hash-Based Folding for Extended-Connectivity Fingerprints

Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM

VA-learning as a more efficient alternative to Q-learning

Revisiting Parallel Context Windows: A Frustratingly Simple Alternative and Chain-of-Thought Deterioration

Can Persistent Homology provide an efficient alternative for Evaluation of Knowledge Graph Completion Methods?

Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling

Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery

Top-Tuning: a study on transfer learning for an efficient alternative to fine tuning for image classification with fast kernel methods

Rethinking Collaborative Metric Learning: Toward an Efficient Alternative without Negative Sampling

When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism