Backward Compatibility During Data Updates by Weight Interpolation

25 January 2023

Papers citing "Backward Compatibility During Data Updates by Weight Interpolation"

9 / 9 papers shown

Title
DEM: Distribution Edited Model for Training with Mixed Data Distributions Dhananjay Ram Aditya Rawal Momchil Hardalov Nikolaos Pappas Sheng Zha MoMe 47 1 0 21 Jun 2024
Improving Prediction Backward-Compatiblility in NLP Model Upgrade with Gated Fusion Yi-An Lai Elman Mansimov Yuqing Xie Yan Zhang 24 3 0 04 Feb 2023
Git Re-Basin: Merging Models modulo Permutation Symmetries Samuel K. Ainsworth J. Hayase S. Srinivasa MoMe 255 316 0 11 Sep 2022
Diverse Weight Averaging for Out-of-Distribution Generalization Alexandre Ramé Matthieu Kirchmeyer Thibaud Rahier A. Rakotomamonjy Patrick Gallinari Matthieu Cord OOD 199 128 0 19 May 2022
ELODI: Ensemble Logit Difference Inhibition for Positive-Congruent Training Yue Zhao Yantao Shen Yuanjun Xiong Shuo Yang Wei Xia Z. Tu Bernt Shiele Stefano Soatto BDL 46 6 0 12 May 2022
Measuring and Reducing Model Update Regression in Structured Prediction for NLP Deng Cai Elman Mansimov Yi-An Lai Yixuan Su Lei Shu Yi Zhang KELM 67 8 0 07 Feb 2022
Fast Model Editing at Scale E. Mitchell Charles Lin Antoine Bosselut Chelsea Finn Christopher D. Manning KELM 230 343 0 21 Oct 2021
Efficient Intent Detection with Dual Sentence Encoders I. Casanueva Tadas Temvcinas D. Gerz Matthew Henderson Ivan Vulić VLM 180 453 0 10 Mar 2020
Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models Cheolhyoung Lee Kyunghyun Cho Wanmo Kang MoE 249 205 0 25 Sep 2019