English
Related papers

Related papers: Understanding Parameter Sharing in Transformers

200 papers

Modern convolutional neural networks (CNNs) have massive identical convolution blocks, and, hence, recursive sharing of parameters across these blocks has been proposed to reduce the amount of parameters. However, naive sharing of…

Computer Vision and Pattern Recognition · Computer Science 2021-11-23 Woochul Kang , Daeyeon Kim

Scaling models has led to significant advancements in deep learning, but training these models in decentralized settings remains challenging due to communication bottlenecks. While existing compression techniques are effective in…

Machine Learning · Computer Science 2025-06-03 Sameera Ramasinghe , Thalaiyasingam Ajanthan , Gil Avraham , Yan Zuo , Alexander Long

Modern Foundation Models (FMs) are typically trained on corpora spanning a wide range of different data modalities, topics and downstream tasks. Utilizing these models can be very computationally expensive and is out of reach for most…

Machine Learning · Computer Science 2025-06-09 Andrey Zhmoginov , Jihwan Lee , Mark Sandler

Transfer learning is widely used to adapt large pretrained models to new tasks with only a small amount of new data. However, a challenge persists -- the features from the original task often do not fully cover what is needed for unseen…

Machine Learning · Computer Science 2026-02-10 Xingyu Alice Yang , Jianyu Zhang , Léon Bottou

Combining multiple machine learning models has long been a technique for enhancing performance, particularly in distributed settings. Traditional approaches, such as model ensembles, work well, but are expensive in terms of memory and…

Machine Learning · Computer Science 2024-12-23 Albert Manuel Orozco Camacho , Stefan Horoi , Guy Wolf , Eugene Belilovsky

Recent developments in large-scale machine learning suggest that by scaling up data, model size and training time properly, one might observe that improvements in pre-training would transfer favorably to most downstream tasks. In this work,…

Machine Learning · Computer Science 2021-10-06 Samira Abnar , Mostafa Dehghani , Behnam Neyshabur , Hanie Sedghi

Reinforcement learning (RL) is well known for requiring large amounts of data in order for RL agents to learn to perform complex tasks. Recent progress in model-based RL allows agents to be much more data-efficient, as it enables them to…

Machine Learning · Computer Science 2021-08-17 Remo Sasso , Matthia Sabatelli , Marco A. Wiering

A substantial gap persists in understanding the reasons behind the exceptional performance of the Transformer architecture in NLP. A particularly unexplored area involves the mechanistic description of how the distribution of parameters…

Computation and Language · Computer Science 2024-03-14 Carlo Nicolini , Jacopo Staiano , Bruno Lepri , Raffaele Marino

In many neural networks, different values of the parameters may result in the same loss value. Parameter space symmetries are loss-invariant transformations that change the model parameters. Teleportation applies such transformations to…

Machine Learning · Computer Science 2024-04-16 Bo Zhao , Robert M. Gower , Robin Walters , Rose Yu

Efficient training and inference algorithms, such as low-rank adaption and model pruning, have shown impressive performance for learning Transformer-based large foundation models. However, due to the technical challenges of the non-convex…

Machine Learning · Computer Science 2024-06-26 Hongkang Li , Meng Wang , Shuai Zhang , Sijia Liu , Pin-Yu Chen

Federated Learning offers a way to train deep neural networks in a distributed fashion. While this addresses limitations related to distributed data, it incurs a communication overhead as the model parameters or gradients need to be…

Machine Learning · Computer Science 2023-05-26 Morten From Elvebakken , Alexandros Iosifidis , Lukas Esterle

Multilingual machine translation suffers from negative interference across languages. A common solution is to relax parameter sharing with language-specific modules like adapters. However, adapters of related languages are unable to…

Computation and Language · Computer Science 2022-12-06 Christos Baziotis , Mikel Artetxe , James Cross , Shruti Bhosale

Model merging dramatically reduces storage and computational resources by combining multiple expert models into a single multi-task model. Although recent model merging methods have shown promising results, they struggle to maintain…

Machine Learning · Computer Science 2025-06-04 Zijing Wang , Xingle Xu , Yongkang Liu , Yiqun Zhang , Peiqin Lin , Shi Feng , Xiaocui Yang , Daling Wang , Hinrich Schütze

With the rapid scaling of large language models (LLMs), serving numerous low-rank adaptations (LoRAs) concurrently has become increasingly impractical, leading to unaffordable costs and necessitating more parameter-efficient finetuning…

Machine Learning · Computer Science 2024-05-28 Sheng Wang , Boyang Xue , Jiacheng Ye , Jiyue Jiang , Liheng Chen , Lingpeng Kong , Chuan Wu

We introduce a parameter sharing scheme, in which different layers of a convolutional neural network (CNN) are defined by a learned linear combination of parameter tensors from a global bank of templates. Restricting the number of templates…

Machine Learning · Computer Science 2019-03-15 Pedro Savarese , Michael Maire

We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…

Computation and Language · Computer Science 2020-10-27 Hyung Won Chung , Thibault Févry , Henry Tsai , Melvin Johnson , Sebastian Ruder

Federated learning is a distributed, privacy-aware learning scenario which trains a single model on data belonging to several clients. Each client trains a local model on its data and the local models are then aggregated by a central party.…

Machine Learning · Computer Science 2020-01-01 Hesham Mostafa

While GPUs are responsible for training the vast majority of state-of-the-art deep learning models, the implications of their architecture are often overlooked when designing new deep learning (DL) models. As a consequence, modifying a DL…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-02-01 Quentin Anthony , Jacob Hatef , Deepak Narayanan , Stella Biderman , Stas Bekman , Junqi Yin , Aamir Shafi , Hari Subramoni , Dhabaleswar Panda

The success of gradient-based meta-learning is primarily attributed to its ability to leverage related tasks to learn task-invariant information. However, the absence of interactions between different tasks in the inner loop leads to…

Machine Learning · Computer Science 2023-12-15 Oscar Chang , Hod Lipson

The growing scale of deep learning models has rendered standard hyperparameter (HP) optimization prohibitively expensive. A promising solution is the use of scale-aware hyperparameters, which can enable direct transfer of optimal HPs from…

Machine Learning · Computer Science 2025-12-30 Nikhil Ghosh , Denny Wu , Alberto Bietti