From Embeddings to Equations: Genetic-Programming Surrogates for Interpretable Transformer Classification

• URL: http://arxiv.org/abs/2509.21341v1
• Date: Tue, 16 Sep 2025 02:17:04 GMT
• Title: From Embeddings to Equations: Genetic-Programming Surrogates for Interpretable Transformer Classification
• Authors: Mohammad Sadegh Khorshidi, Navid Yazdanjue, Hassan Gharoun, Mohammad Reza Nikoo, Fang Chen, Amir H. Gandomi,
• Abstract summary: We study symbolic surrogate modeling of frozen Transformer embeddings to obtain compact, auditable classifiers with calibrated probabilities.<n>For five benchmarks (SST2G, 20NG, MNIST, CIFAR10, MSC17), embeddings from ModernBERT, DINOv2, and SigLIP are partitioned on the training set into disjoint, information-preserving views.<n>A cooperative multi-population genetic program (MEGP) then learns additive, closed-form logit programs over these views.
• Score: 9.17282078449475
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study symbolic surrogate modeling of frozen Transformer embeddings to obtain compact, auditable classifiers with calibrated probabilities. For five benchmarks (SST2G, 20NG, MNIST, CIFAR10, MSC17), embeddings from ModernBERT, DINOv2, and SigLIP are partitioned on the training set into disjoint, information-preserving views via semantic-preserving feature partitioning (SPFP). A cooperative multi-population genetic program (MEGP) then learns additive, closed-form logit programs over these views. Across 30 runs per dataset we report F1, AUC, log-loss, Brier, expected calibration error (ECE), and symbolic complexity; a canonical model is chosen by a one-standard-error rule on validation F1 with a parsimony tie-break. Temperature scaling fitted on validation yields substantial ECE reductions on test. The resulting surrogates achieve strong discrimination (up to F1 around 0.99 on MNIST, CIFAR10, MSC17; around 0.95 on SST2G), while 20NG remains most challenging. We provide reliability diagrams, dimension usage and overlap statistics, contribution-based importances, and global effect profiles (PDP and ALE), demonstrating faithful, cross-modal explanations grounded in explicit programs.

Related papers

• From Global to Granular: Revealing IQA Model Performance via Correlation Surface [83.65597122328133]
  We present textbfGranularity-Modulated Correlation (GMC), which provides a structured, fine-grained analysis of IQA performance.<n>GMC includes a textbfDistribution Regulator that regularizes correlations to mitigate biases from non-uniform quality distributions.<n>Experiments on standard benchmarks show that GMC reveals performance characteristics invisible to scalar metrics, offering a more informative and reliable paradigm for analyzing, comparing, and deploying IQA models.
  arXiv  Detail & Related papers  (2026-01-29T13:55:26Z)
• GraphPerf-RT: A Graph-Driven Performance Model for Hardware-Aware Scheduling of OpenMP Codes [7.204137900029132]
  We introduce GraphPerf-RT, the first surrogate that unifies task DAG topology, CFG-derived code semantics, and runtime context.<n>We validate GraphPerf-RT on three embedded ARM platforms (Jetson TX2, Jetson Orin NX, RUBIK Pi)<n>Experiments show that GraphPerf-RT achieves 66% makespan reduction (0.97 +/- 0.35s) and 82% energy reduction (0.006 +/- 0.005J) compared to model-free baselines.
  arXiv  Detail & Related papers  (2025-12-12T23:46:05Z)
• A transfer learning approach for automatic conflicts detection in software requirement sentence pairs based on dual encoders [5.780557526613627]
  This paper proposes a Transferable Software Requirement Conflict Detection Framework based on SBERT and SimCSE.<n>The proposed framework achieves a 10.4% improvement in both macro-F1 and weighted-F1 scores in in-domain settings, and an 11.4% increase in macro-F1 in cross-domain scenarios.
  arXiv  Detail & Related papers  (2025-11-28T09:16:35Z)
• Unsupervised Conformal Inference: Bootstrapping and Alignment to Control LLM Uncertainty [49.19257648205146]
  We propose an unsupervised conformal inference framework for generation.<n>Our gates achieve close-to-nominal coverage and provide tighter, more stable thresholds than split UCP.<n>The result is a label-free, API-compatible gate for test-time filtering.
  arXiv  Detail & Related papers  (2025-09-26T23:40:47Z)
• PRISM: Distributed Inference for Foundation Models at Edge [73.54372283220444]
  PRISM is a communication-efficient and compute-aware strategy for distributed Transformer inference on edge devices.<n>We evaluate PRISM on ViT, BERT, and GPT-2 across diverse datasets.
  arXiv  Detail & Related papers  (2025-07-16T11:25:03Z)
• Prior2Former -- Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation [74.55677741919035]
  We propose Prior2Former (P2F), the first approach for segmentation vision transformers rooted in evidential learning.<n>P2F extends the mask vision transformer architecture by incorporating a Beta prior for computing model uncertainty in pixel-wise binary mask assignments.<n>Unlike most segmentation models addressing unknown classes, P2F operates without access to OOD data samples or contrastive training on void (i.e., unlabeled) classes.
  arXiv  Detail & Related papers  (2025-04-07T08:53:14Z)
• Harnessing Mixed Features for Imbalance Data Oversampling: Application to Bank Customers Scoring [5.091061468748012]
  We introduce MGS-GRF, an oversampling strategy designed for mixed features.<n>We show that MGS-GRF exhibits two important properties: (i) the coherence i.e. the ability to only generate combinations of categorical features that are already present in the original dataset and (ii) association, i.e. the ability to preserve the dependence between continuous and categorical features.
  arXiv  Detail & Related papers  (2025-03-26T08:53:40Z)
• Coping with Change: Learning Invariant and Minimum Sufficient Representations for Fine-Grained Visual Categorization [26.254072665916155]
  Fine-grained visual categorization (FGVC) is a challenging task due to similar visual appearances between various species. Previous studies assume that the training and test data have the same underlying distributions, and that features extracted by modern backbone architectures remain discriminative and generalize well to unseen test data. We combine the merits of invariant risk minimization (IRM) and information bottleneck (IB) principle to learn invariant and minimum sufficient (IMS) representations for FGVC.
  arXiv  Detail & Related papers  (2023-06-08T02:45:15Z)
• Federated Conformal Predictors for Distributed Uncertainty Quantification [83.50609351513886]
  Conformal prediction is emerging as a popular paradigm for providing rigorous uncertainty quantification in machine learning. In this paper, we extend conformal prediction to the federated learning setting. We propose a weaker notion of partial exchangeability, better suited to the FL setting, and use it to develop the Federated Conformal Prediction framework.
  arXiv  Detail & Related papers  (2023-05-27T19:57:27Z)
• Feature Quantization Improves GAN Training [126.02828112121874]
  Feature Quantization (FQ) for the discriminator embeds both true and fake data samples into a shared discrete space. Our method can be easily plugged into existing GAN models, with little computational overhead in training.
  arXiv  Detail & Related papers  (2020-04-05T04:06:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.