AI Paper Atlas

Research map / Federated learning and privacy / Privacy attacks and secure learning

Privacy Enhanced Multimodal Neural Representations for Emotion Recognition

Mimansa Jaiswal, Emily Mower Provost

AAAI 2020 · Federated learning and privacy › Privacy attacks and secure learning · approach: Visual privacy and face de-identification · 68 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
adversarially train representations to hide genderEmotion recognition models · Multiple datasets and modalitiesprivacy metric: privacy metric is always higher when the representations are trained adversariallyImproved
adversarially train representations to hide genderEmotion recognition models · Multiple datasets and modalitiesemotion recognition UARNo clear effect
adversarially train representations to hide genderUnimodal lexical emotion models · MuSE and IEMOCAPemotion recognition UARImproved
increase adversarial strength from λ=0.50 to λ=0.75 (ablation)Unimodal acoustic MuSE · MuSEprivacy metric: 0.39 to 0.45Improved
increase adversarial strength from λ=0.75 to λ=1.00 (ablation)Unimodal acoustic MuSE · MuSEprivacy metric: 0.45 to 0.41Hurt
apply separate adversarial components after pooling each modality (ablation)Multimodal emotion recognition · MuSE and IEMOCAPprivacy metric: Iem - U: 0.66, P: 0.43; MuS - U: 0.63, P: 0.44; Valence: Iem - U: 0.67, P: 0.46; MuS - U: 0.64, P: 0.46Improved
replace gender invariance with speaker-identity invariance (ablation)Emotion recognition models · Multiple datasetsmembership identification UAR: Activation: Imp - 0.58, Pod - 0.60, Iem - 0.58, MuS - 0.62; Valence: Imp - 0.54, Pod - 0.56, Iem - 0.59, MuS - 0.60Improved
add speaker-identity invariance alongside gender invariance (ablation)Emotion recognition models · Multiple datasets and modalitiesmembership identification UAR: 0.58Improved
add speaker-identity invariance alongside gender invariance (ablation)Emotion recognition models · MuSE activationemotion recognition UAR: 0.66 to 0.65Hurt
use multimodal rather than unimodal representationsGeneral emotion recognition models · MuSE and IEMOCAPgender leakage: Activation: Iem 0.74, MuS 0.73; valence: Iem 0.68, MuS 0.64Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy