Invariant Representations through Adversarial Forgetting

2019-11-11 · Ayush Jaiswal, Daniel Moyer, Greg Ver Steeg, Wael Abd-Almageed, Premkumar Natarajan

We propose a novel approach to achieving invariance for deep neural networks in the form of inducing amnesia to unwanted factors of data through a new adversarial forgetting mechanism. We show that the forgetting mechanism serves as an information-bottleneck, which is manipulated by the adversarial training to learn invariance to unwanted factors. Empirical results show that the proposed framework achieves state-of-the-art performance at learning invariance in both nuisance and bias settings on a diverse collection of datasets and tasks.

📄 PDF Abstract BibTeX arXiv:1911.04060

Code (0)

등록된 구현이 없습니다.

mask-Net: Learning Context Aware Invariant Features using Adversarial Forgetting (Student Abstract)

2020-11-25 · Hemant Yadav, Atul Anshuman Singh, Rachit Mittal, Sunayana Sitaram 외

Training a robust system, e.g.,Speech to Text (STT), requires large datasets. Variability present in the dataset such as unwanted nuisances and biases are the reason for the need of large datasets to learn general repres…

Speech-to-Text

Adversarial Continual Learning

2020-03-21 · ECCV 2020 8 · Sayna Ebrahimi, Franziska Meier, Roberto Calandra, Trevor Darrell 외

Continual learning aims to learn new tasks without forgetting previously learned ones. We hypothesize that representations learned to solve each task in a sequence have a shared structure while containing some task-speci…

Continual Learning image-classification Image Classification

Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation

2022-10-10 · Peiyi Wang, YiFan Song, Tianyu Liu, Binghuai Lin 외

Continual relation extraction (CRE) aims to continually learn new relations from a class-incremental data stream. CRE model usually suffers from catastrophic forgetting problem, i.e., the performance of old relations ser…

Continual Relation Extraction Relation Relation Extraction

Self-Supervised GAN to Counter Forgetting

2018-10-27 · Ting Chen, Xiaohua Zhai, Neil Houlsby

GANs involve training two networks in an adversarial game, where each network's task depends on its adversary. Recently, several works have framed GAN training as an online or continual learning problem. We focus on the …

Continual Learning General Classification

DIB-OD: Preserving the Invariant Core for Robust Heterogeneous Graph Adaptation via Decoupled Information Bottleneck and Online Distillation

2026-04-13 · Yang Yan, Qiuyan Wang, Tianjin Huang, Qiudong Yu 외 arxiv

Graph Neural Network pretraining is pivotal for leveraging unlabeled graph data. However, generalizing across heterogeneous domains remains a major challenge due to severe distribution shifts. Existing methods primarily …

Graph Neural Network Domain Adaptation