KINDER: Kernel-based Independence for Fair Representation Learning via Prototype-space Erasure
Organizations: University of Tübingen · Zuse School ELIZA · Middle East Technical University · Harvard University ·
Abstract
Concept erasure is a prominent approach to achieving fairness in machine learning through the removal of sensitive attributes from learned representations. Prior concept erasure methods typically define debiasing indirectly through the failure of a chosen adversary, probe, or fairness penalty, which makes the target of erasure dependent on a particular decoder family or optimization setup. We introduce KINDER, which directly removes sensitive-attribute information from intermediate representations with respect to a chosen family of prototype functionals, and is compatible with any deep model containing an intermediate feature space, independent of the architecture, task type, or training paradigm. KINDER operates in a random Fourier feature space, where it estimates a sensitive subspace from protected group prototypes and projects representations onto its orthogonal complement. Thus, it forms an explicit representation cleaning mechanism distinct from prior fairness control studies. We conduct extensive experiments across diverse settings and show the effectiveness of KINDER on (i) supervised and self-supervised settings, (ii) classification, regression, and image segmentation tasks, and (iii) diverse data modalities, including visual, textual, and tabular data. Code and trained models are available at: https://github.com/abtinmU/KINDER
Figures & tables
| Method | Independence type | Erasure target | Subspace source | Data | Task | Set. | Inter. |
| INLP Ravfogel et al. (2020) | , linear | Linear probe failure | Iterative probes; nullspace | T | C | P | NR |
| RLACE Ravfogel et al. (2022a) | , linear | Linear adversary failure | Linear minmax subspace | T | C | P | NR |
| KCE Ravfogel et al. (2022b) | , for some kernel | Kernel adversary failure | Kernelized minmax subspace | T | C | P | NR |
| SAL Shao et al. (2023) | , for | High-covariance directions | Covariance SVD projection | T | C | P | NR |
| top spectral linear pairs | |||||||
| LEACE Belrose et al. (2023) | , linear | Linear classifier failure | Covariance projection | T | C | P | NR |
| Method | BIOS | MOJI | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Acc | F1 | WgF1 | WCTG | RCTG | Acc | F1 | WgF1 | WCTG | RCTG | |
| BERT | 80.9 | 74.4 | 70.7 | 47.3 | 16.2 | 80.1 | 74.7 | 62.1 | 25.6 | 17.5 |
| + INLP | 80.7 | 74.2 | 70.3 | 45.5 | 14.9 | 79.8 | 74.7 | 61.5 | 25.3 | 17.9 |
| + RLACE | 79.8 | 73.1 | 69.1 | 46.8 | 14.8 | 79.1 | 73.7 | 61.0 | 23.9 | 16.9 |
| + LEACE | 80.7 | 74.3 | 70.5 | 45.2 | 14.5 | 79.9 | 74.8 | 61.1 | 26.3 | 18.6 |
| + KCE | 79.8 | 72.5 | 68.6 | 49.3 | 16.5 | 79.2 | 73.9 | 61.4 | 23.6 | 16.7 |
| Method | Perf. | Race | Gender | Ethnicity | Inter. | |||||
|---|---|---|---|---|---|---|---|---|---|---|
| Dice | HD95 | D-WG | H-Gap | D-WG | H-Gap | D-WG | H-Gap | D-WG | H-Gap | |
| UNet | 81.4 | 6.8 | 77.4 | 4.1 | 81.3 | 0.7 | 81.3 | 1.2 | 67.5 | 30.7 |
| + INLP | 82.6 | 5.5 | 78.7 | 3.0 | 82.6 | 1.0 | 82.6 | 0.1 | 70.5 | 20.0 |
| + RLACE | 83.3 | 5.1 | 80.0 | 2.8 | 83.2 | 0.3 | 83.2 | 0.2 | 73.1 | 17.0 |
| + LEACE | 83.5 | 4.7 | 80.3 | 1.2 | 83.5 | 0.6 | 83.4 | 0.8 | 76.6 | 6.0 |
| + SUP | 83.0 | 5.5 | 79.1 | 3.7 | 83.0 | 0.8 | 82.9 | 1.4 | 68.7 | 30.8 |
| Method | Acc | F1 | Gender Gap | Race Gap | Age Gap | Inter. Gap | WG Inter. |
|---|---|---|---|---|---|---|---|
| TabM | 91.9 | 39.9 | 2.1 | 23.2 | 2.5 | 46.6 | 65.8 |
| + INLP | 79.5 | 43.6 | 1.6 | 22.1 | 5.2 | 53.3 | 58.3 |
| + RLACE | 78.5 | 43.0 | 2.4 | 20.7 | 7.1 | 53.1 | 58.3 |
| + LEACE | 78.3 | 42.6 | 2.3 | 21.4 | 6.2 | 54.4 | 58.3 |
| + KCE | 80.1 | 18.0 | 0.4 | 46.2 | 4.1 | 73.6 | 35.7 |
| + KINDER | 80.6 | 44.7 | 1.2 | 22.5 | 7.1 | 46.6 | 68.7 |
| Method | Acc. | Gender Gap | Age Gap | Inter. Gap | WG-Inter. |
|---|---|---|---|---|---|
| I-JEPA | 91.1 | 6.6 | 2.7 | 11.5 | 87.7 |
| + INLP | 85.7 | 3.4 | 8.5 | 13.7 | 82.7 |
| + LEACE | 90.0 | 6.3 | 5.8 | 12.0 | 86.3 |
| + RLACE | 91.8 | 6.1 | 2.6 | 10.8 | 88.5 |
| + KCE | 91.8 | 7.0 | 2.5 | 11.4 | 88.3 |
| + SUP | 91.9 | 6.0 | 2.7 | 11.0 | 88.5 |
| Method | MAE | Race WG-MAE | Gender WG-MAE | Age WG-MAE | Inter. WG-MAE | |
|---|---|---|---|---|---|---|
| ResNet | 2.59 | 0.15 | 3.24 | 2.61 | 2.78 | 5.55 |
| + INLP | 2.96 | 0.00 | 3.75 | 3.01 | 3.28 | 10.88 |
| + LEACE | 2.77 | 0.11 | 3.25 | 2.79 | 3.01 | 5.91 |
| + RLACE | 2.77 | 0.11 | 3.27 | 2.79 | 3.02 | 5.93 |
| + KCE | 2.57 | 0.15 | 3.23 | 2.59 | 2.84 | 5.10 |
| + SUP | 2.77 | 0.11 | 3.29 | 2.79 | 3.03 | 5.90 |
| Method | Acc | Race Gap | Gender Gap | Ethnicity Gap | Inter. Gap | WG-Inter. |
|---|---|---|---|---|---|---|
| FactorCL | 60.4 | 12.8 | 4.3 | 15.6 | 95.8 | 0.0 |
| + INLP | 60.2 | 7.9 | 5.6 | 10.3 | 76.0 | 25.0 |
| + RLACE | 60.0 | 13.7 | 4.2 | 16.9 | 95.9 | 0.0 |
| + LEACE | 57.3 | 4.3 | 3.7 | 7.3 | 84.8 | 0.0 |
| + KCE | 58.8 | 9.1 | 5.8 | 15.7 | 93.5 | 0.0 |
| + SUP | 60.6 | 12.3 | 2.3 | 17.7 | 95.8 | 0.0 |
Appendix figures & tables15 assets
Supplementary material from the paper’s appendix.
Appendix
| Dataset | Task / target | Outcome | Smallest group per attribute | Worst split imbalance | |
|---|---|---|---|---|---|
| FairSeg | Segmentation disc/cup mask | 9,432 | mask target | race: Asian, 9.2%, gender: male, 41.5%, ethnicity: Hispanic, 3.9%, | Asian male Hispanic %, |
| FairVLMed | Binary classification glaucoma | 9,460 | positive 50.6% | race: Asian, 8.3%, gender: male, 43.6%, ethnicity: Hispanic, 4.2%, | positive Asian male Hispanic %, |
| MIMIC-IV ICU mortality | Binary classification hospital mortality | 72,114 | positive 10.1% | gender: female, 45.0%, race: NHPI, 0.2%, age: 50, 16.4%, | positive female AIAN 50 %, |
| MIMIC-IV ICU LOS | Regression ICU length of stay | 56,527 | median 2.36 IQR 1.55–4.29 | gender: female, 44.2%, race: NHPI, 0.2%, age: 18–39, 7.9%, | intersectional target-mean shift 5.8 |
| Bias for Bios | Multiclass classification profession | 396,189 | 28 classes class | gender: group 1, 46.1%, | profession 23 group 1 %, |
| Moji 90% | Binary classification sentiment | 100,000 | positive 50.0% | dialect: protected=0, 50.0%, | negative protected=1 5.0%, |
| Method | Method fitting (s) | Total pipeline (s) | Peak GPU (GB) | Peak RAM (GB) |
|---|---|---|---|---|
| TabM | – | 21.6 | 0.147 | 1.832 |
| INLP | 171.7 | 195.1 | 0.147 | 3.654 |
| LEACE | 1.4 | 24.8 | 0.147 | 3.129 |
| SAL | 7.2 | 30.2 | 0.147 | 3.943 |
| KCE | 150.1 | 173.2 | 0.682 | 6.721 |
| RLACE | 217.4 | 240.8 | 0.147 | 5.677 |
| Representation | Projection Shift | RBF-HSIC( , ) | Mean Gap | Cov. Gap | 3rd-Moment Gap | Removed Rank |
|---|---|---|---|---|---|---|
| Raw encoder | – | – | 1.164 | 1.457 | 1.793 | 0 |
| Raw RFF | 0.000 | 1.000 | 1.000 | 1.000 | 1.000 | 0 |
| KINDER -order 1 | 0.155 | 0.975 | 0.998 | 0.980 | 0.931 | 1 |
| KINDER -order 2 | 0.362 | 0.687 | 0.679 | 0.279 | 0.263 | 3 |
| KINDER -order 3 | 0.540 | 0.433 | 0.563 | 0.124 | 0.065 | 4 |
| Baseline | Metric | Baseline value | KINDER value | Improvement | 95% CI | one-sided | BH | Signif. |
|---|---|---|---|---|---|---|---|---|
| SUP | RBF-HSIC | 0.89 | 0.46 | 0.43 | [0.33, 0.70] | 0.003 | 0.005 | ** |
| SUP | Average gap | 0.96 | 0.27 | 0.69 | [0.64, 0.80] | 0.003 | 0.005 | ** |
| INLP | RBF-HSIC | 0.56 | 0.46 | 0.09 | [0.05, 0.46] | 0.010 | 0.013 | |
| INLP | Average gap | 0.89 | 0.27 | 0.62 | [0.56, 0.75] | 0.003 | 0.005 | ** |
| RLACE | RBF-HSIC | 1.01 | 0.46 | 0.55 | [0.42, 0.77] | 0.003 | 0.005 | ** |
| RLACE | Average gap | 0.96 | 0.27 | 0.69 | [0.63, 0.79] | 0.003 | 0.005 | ** |
| Method | Acc | F1 | Gender Gap | Race Gap | Age Gap | Inter. Gap | WorstGroupAcc |
|---|---|---|---|---|---|---|---|
| ResNet | 0.92 | 0.40 | 0.02 | 0.23 | 0.03 | 0.47 | 0.66 |
| + INLP-seq | 0.78 | 0.43 | 0.02 | 0.22 | 0.06 | 0.53 | 0.57 |
| + RLACE-seq | 0.78 | 0.43 | 0.03 | 0.23 | 0.07 | 0.53 | 0.58 |
| + LEACE-seq | 0.81 | 0.44 | 0.01 | 0.25 | 0.05 | 0.73 | 0.38 |
| + KCE-seq | 0.80 | 0.20 | 0.02 | 0.19 | 0.04 | 0.76 | 0.00 |
| + KINDER -seq | 0.79 | 0.43 | 0.02 | 0.16 | 0.08 | 0.46 | 0.50 |
| Method | MAE | (%) | Race WG | Race Gap |
|---|---|---|---|---|
| MLP-PLR | 0.093 | 63.8 | 0.154 | 0.090 |
| + INLP | 0.148 | 18.2 | 0.288 | 0.164 |
| + LEACE | 0.157 | 11.7 | 0.359 | 0.225 |
| + RLACE | 0.094 | 63.8 | 0.152 | 0.071 |
| + KCE | 0.096 | 60.2 | 0.190 | 0.113 |
| + SUP | 0.094 | 63.8 | 0.149 | 0.070 |
| Method | Acc | F1 | Gender Gap | Race Gap | Age Gap | Inter. Gap | WG Inter. |
|---|---|---|---|---|---|---|---|
| TabM | 91.95 0.07 | 41.72 1.49 | 1.15 0.33 | 20.63 1.82 | 3.25 1.01 | 70.83 0.00 | 50.00 0.00 |
| + INLP | 77.67 3.59 | 41.95 2.96 | 1.70 0.79 | 21.48 2.31 | 5.62 0.91 | 49.63 3.97 | 57.82 10.80 |
| + RLACE | 77.65 2.93 | 42.14 2.18 | 1.73 0.52 | 22.38 3.04 | 7.95 0.91 | 47.98 2.04 | 57.64 8.87 |
| + LEACE | 77.82 2.52 | 42.20 1.67 | 1.98 0.39 | 20.88 1.47 | 6.77 1.22 | 44.72 2.68 | 56.06 8.37 |
| + KCE | 78.83 2.04 | 17.46 1.18 | 1.26 0.52 | 16.96 6.68 | 4.34 0.35 | 74.42 4.04 | 46.67 7.45 |
| + SAL | 77.01 2.34 | 41.66 1.61 | 1.85 0.60 | 21.63 3.08 | 7.02 0.69 | 47.41 3.49 | 51.82 6.89 |
| Method | MAE | Race WG-MAE | Gender WG-MAE | Age WG-MAE | Inter. WG-MAE | |
|---|---|---|---|---|---|---|
| MLP-PLR | 2.62 0.05 | 0.12 0.00 | 3.39 0.06 | 2.64 0.05 | 2.88 0.06 | 8.00 1.21 |
| + INLP | 2.73 0.13 | 0.09 0.05 | 3.50 0.13 | 2.76 0.14 | 2.98 0.16 | 8.29 1.87 |
| + LEACE | 2.70 0.01 | 0.08 0.02 | 3.48 0.06 | 2.74 0.01 | 2.84 0.06 | 8.49 2.16 |
| + SUP | 2.68 0.00 | 0.08 0.03 | 3.51 0.05 | 2.71 0.02 | 2.95 0.08 | 7.40 1.96 |
| + SAL | 2.70 0.01 | 0.08 0.03 | 3.54 0.07 | 2.71 0.02 | 2.92 0.09 | 8.27 2.14 |
| + KINDER | 2.54 0.04 ** | 0.11 0.00 * | 3.31 0.06 *** | 2.55 0.05 ** | 2.78 0.07 ** | 8.80 0.16 |
| Method | Perf. | Race | Gender | Ethnicity | Inter. | |||||
|---|---|---|---|---|---|---|---|---|---|---|
| Dice | HD95 | D-WG | Dice Gap | D-WG | Dice Gap | D-WG | Dice Gap | D-WG | Dice Gap | |
| Backbone | 83.12 1.22 | 5.12 1.19 | 78.25 0.97 | 4.03 0.29 | 82.93 1.17 | 0.37 0.24 | 82.02 0.53 | 1.60 0.34 | 65.88 2.62 | 16.00 10.18 |
| + INLP | 83.42 1.07 | 4.82 0.72 | 78.43 1.45 | 3.85 0.66 | 83.22 0.91 | 0.50 0.35 | 82.38 0.87 | 1.32 0.82 | 66.53 4.33 | 13.35 5.81 |
| + RLACE | 83.70 0.72 | 4.72 0.64 | 78.97 1.01 | 3.80 0.67 | 83.58 0.69 | 0.20 0.12 | 82.52 0.96 | 1.42 0.86 | 67.92 3.83 | 11.50 3.99 |
| + LEACE | 83.68 0.81 | 4.60 0.73 | 79.10 1.28 | 3.18 1.32 | 83.52 0.81 | 0.32 0.19 | 82.52 1.11 | 1.58 0.56 | 69.22 5.34 | 8.22 2.42 |
| + SUP | 83.60 0.82 | 4.90 0.88 | 78.68 1.12 | 3.97 0.34 | 83.50 0.70 | 0.30 0.36 | 82.55 0.84 | 1.60 0.22 | 65.65 2.86 | 16.98 9.37 |
| Method | Acc | F1 | WgF1 | WCTG | RCTG |
|---|---|---|---|---|---|
| BERT | 80.12 0.04 | 70.98 0.05 | 66.42 0.07 | 52.40 0.18 | 19.58 0.11 |
| + INLP | 79.04 0.05 | 68.53 0.04 | 66.91 0.11 | 46.64 0.22 | 14.65 0.21 |
| + RLACE | 79.82 0.06 | 70.52 0.11 | 67.70 0.01 | 51.28 0.65 | 16.22 0.07 |
| + LEACE | 79.38 0.04 | 70.08 0.09 | 67.05 0.05 | 47.90 0.15 | 12.96 0.07 |
| + KCE | 78.22 2.25 | 70.40 2.89 | 66.63 3.50 | 49.78 2.97 | 16.25 3.10 |
| + SUP | 79.52 0.08 | 70.18 0.14 | 65.82 0.18 | 51.35 0.45 | 18.31 0.20 |
| Method | Acc | F1 | Gender Gap | Race Gap | Age Gap | Inter. Gap | WG Inter. |
|---|---|---|---|---|---|---|---|
| TabM | 91.95 0.07 | 41.72 1.49 | 1.15 0.33 | 20.63 1.82 | 3.25 1.01 | 70.83 0.00 | 50.00 0.00 |
| + FR-Train | 91.67 0.05 | 38.39 3.35 | 0.34 0.20 | 21.61 3.31 | 3.45 0.99 | 70.83 0.00 | 50.00 0.00 |
| + FairMixup | 80.59 0.59 | 44.66 0.42 | 1.34 0.62 | 24.48 1.34 | 7.38 0.51 | 50.02 2.66 | 60.91 6.10 |
| + GroupDRO | 91.31 0.27 | 40.58 3.73 | 1.07 0.55 | 26.36 11.44 | 3.11 1.06 | 71.00 2.66 | 56.00 13.42 |
| + FairBatch | 91.65 0.13 | 39.66 3.22 | 0.47 0.33 | 29.96 6.90 | 4.11 1.30 | 73.33 2.28 | 50.00 0.00 |
| + KINDER (NH) | 92.05 0.07 ** | 46.17 1.35 * | 0.88 0.39 | 22.10 8.28 | 2.23 0.27 * | 72.22 2.41 | 50.00 0.00 |
| Method | Acc | F1 | Gender Gap | Race Gap | Age Gap | Inter. Gap | WG Inter. |
|---|---|---|---|---|---|---|---|
| + SAL | 77.01 2.34 | 41.66 1.61 | 1.85 0.60 | 21.63 3.08 | 7.02 0.69 | 47.41 3.49 | 51.82 6.89 |
| + KINDER post-hoc (Order 1) | 80.22 1.07 | 44.32 0.93 | 1.22 0.68 | 21.15 2.57 | 6.97 0.65 | 56.53 13.53 | 55.56 9.62 |
| + KINDER (Order 1) | 80.72 1.52 | 45.38 1.16 | 1.51 0.23 | 22.61 3.08 | 6.24 0.52 | 49.81 3.13 | 64.65 1.75 |
| + KINDER (NH, Order 1) | 91.93 0.02 | 48.62 1.50 | 1.17 0.33 | 28.08 3.75 | 2.87 0.42 | 75.00 0.00 | 50.00 0.00 |
| Method | MAE | Race WG-MAE | Gender WG-MAE | Age WG-MAE | Inter. WG-MAE | |
|---|---|---|---|---|---|---|
| + SAL | 2.70 0.01 | 0.08 0.03 | 3.54 0.07 | 2.71 0.02 | 2.92 0.09 | 8.27 2.14 |
| + KINDER (Order 1) | 2.56 0.09 | 0.12 0.00 | 3.37 0.16 | 2.58 0.10 | 2.81 0.10 | 10.12 0.25 |
| Method | Acc | F1 | WgF1 | WCTG | RCTG |
|---|---|---|---|---|---|
| + SAL | 79.11 0.01 | 69.95 0.08 | 66.95 0.13 | 47.81 0.30 | 13.05 0.20 |
| + KINDER (Order 1) | 82.00 0.04 | 73.54 0.26 | 70.99 0.31 | 47.79 2.54 | 13.98 0.68 |
| Method | Perf. | Race | Gender | Ethnicity | Inter. | |||||
|---|---|---|---|---|---|---|---|---|---|---|
| Dice | HD95 | D-WG | Dice Gap | D-WG | Dice Gap | D-WG | Dice Gap | D-WG | Dice Gap | |
| + SAL | 83.97 0.68 | 4.43 0.59 | 78.63 0.86 | 4.03 0.06 | 83.63 0.50 | 0.40 0.17 | 82.27 0.78 | 2.07 0.15 | 65.87 0.61 | 9.57 1.55 |
| + KINDER (Order 1) | 84.00 0.22 | 4.18 0.29 | 79.40 0.71 | 3.38 1.23 | 83.78 0.15 | 0.25 0.13 | 82.80 0.62 | 1.45 0.91 | 70.18 5.38 | 7.43 1.52 |
Debiased ML
Debiased machine learning develops methods to reduce unfair or spurious model behavior and statistical bias in learned estimates.
See all 57 papers