Sparse-by-Design Cross-Modality Prediction: L0-Gated Representations for Reliable and Efficient Learning

• URL: http://arxiv.org/abs/2603.26801v1
• Date: Thu, 26 Mar 2026 03:33:42 GMT
• Title: Sparse-by-Design Cross-Modality Prediction: L0-Gated Representations for Reliable and Efficient Learning
• Abstract summary: A unified sparsification primitive would make accuracy-efficiency trade-offs comparable across modalities.<n>We propose a modality-agnostic, feature-wise hard-concrete gating framework that enforces L0-style sparsity directly on learned representations.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Predictive systems increasingly span heterogeneous modalities such as graphs, language, and tabular records, but sparsity and efficiency remain modality-specific (graph edge or neighborhood sparsification, Transformer head or layer pruning, and separate tabular feature-selection pipelines). This fragmentation makes results hard to compare, complicates deployment, and weakens reliability analysis across end-to-end KDD pipelines. A unified sparsification primitive would make accuracy-efficiency trade-offs comparable across modalities and enable controlled reliability analysis under representation compression. We ask whether a single representation-level mechanism can yield comparable accuracy-efficiency trade-offs across modalities while preserving or improving probability calibration. We propose L0-Gated Cross-Modality Learning (L0GM), a modality-agnostic, feature-wise hard-concrete gating framework that enforces L0-style sparsity directly on learned representations. L0GM attaches hard-concrete stochastic gates to each modality's classifier-facing interface: node embeddings (GNNs), pooled sequence embeddings such as CLS (Transformers), and learned tabular embedding vectors (tabular models). This yields end-to-end trainable sparsification with an explicit control knob for the active feature fraction. To stabilize optimization and make trade-offs interpretable, we introduce an L0-annealing schedule that induces clear accuracy-sparsity Pareto frontiers. Across three public benchmarks (ogbn-products, Adult, IMDB), L0GM achieves competitive predictive performance while activating fewer representation dimensions, and it reduces Expected Calibration Error (ECE) in our evaluation. Overall, L0GM establishes a modality-agnostic, reproducible sparsification primitive that supports comparable accuracy, efficiency, and calibration trade-off analysis across heterogeneous modalities.

Related papers

• DIFF-ERO: A Conformance-Aware Loss for Deep Learning in Process Mining [8.304025820176394]
  We introduce DIFF-ERO, a conformance-aware loss function for deep learning models on process data.<n>DIFF-ERO is a differentiable formulation of entropy-based conformance that incorporates control-flow information during training.<n>We show improved predictive performance where structure matters most while maintaining parity elsewhere.
  arXiv  Detail & Related papers  (2026-06-12T09:06:05Z)
• Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibration [76.08899010904652]
  CapCal is a training-free framework that mechanically decouples positional bias from ranking decisions.<n>It achieves superior performance among training-free methods while preserving single-pass efficiency.
  arXiv  Detail & Related papers  (2026-04-11T10:47:22Z)
• Variational Rectification Inference for Learning with Noisy Labels [74.85528327499662]
  We propose variational rectification inference (VRI) to formulate the adaptive rectification for loss functions.<n>VRI is constructed as a hierarchical Bayes by treating the rectifying vector as a latent variable.<n>By introducing the variational term in VRI, the conditional posterior is estimated accurately and avoids collapsing to a Dirac delta function.
  arXiv  Detail & Related papers  (2026-03-18T01:25:08Z)
• Silent Inconsistency in Data-Parallel Full Fine-Tuning: Diagnosing Worker-Level Optimization Misalignment [27.352639822596146]
  Cross-worker divergence in losses and gradients can remain invisible under conventional monitoring signals.<n>We propose a model-agnostic diagnostic framework that quantifies worker-level consistency using training signals readily available in standard pipelines.
  arXiv  Detail & Related papers  (2026-02-16T04:42:30Z)
• EST: Towards Efficient Scaling Laws in Click-Through Rate Prediction via Unified Modeling [13.693397814262681]
  Efficiently scaling industrial Click-Through Rate (CTR) prediction has recently attracted significant research attention.<n>We propose the Efficiently Scalable Transformer (EST), which achieves fully unified modeling by processing all raw inputs in a single sequence without lossy aggregation.<n>EST significantly outperforms production baselines, delivering a 3.27% RPM (Revenue Per Mile) increase and a 1.22% CTR lift.
  arXiv  Detail & Related papers  (2026-02-11T12:51:54Z)
• AGDC: Autoregressive Generation of Variable-Length Sequences with Joint Discrete and Continuous Spaces [33.91616464118993]
  Transformer-based autoregressive models excel in data generation but are inherently constrained by their reliance on discretized tokens.<n>We analyze the scalability limitations of existing discretization-based approaches for generating hybrid discrete-continuous sequences.<n>We propose AGDC, a novel unified framework that jointly models discrete and continuous values for variable-length sequences.
  arXiv  Detail & Related papers  (2026-01-09T09:57:12Z)
• Sparse Attention Post-Training for Mechanistic Interpretability [55.030850996535776]
  We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance.<n>Applying a flexible sparsity regularisation under a constrained-loss objective, we show on models up to 1B parameters that it is possible to retain the original pretraining loss while reducing attention connectivity to $approx 0.3 % of its edges.
  arXiv  Detail & Related papers  (2025-12-05T16:40:08Z)
• 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)
• LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks [52.46420522934253]
  We introduce LoRA-Ensemble, a parameter-efficient ensembling method for self-attention networks.<n>The method not only outperforms state-of-the-art implicit techniques like BatchEnsemble, but even matches or exceeds the accuracy of an Explicit Ensemble.
  arXiv  Detail & Related papers  (2024-05-23T11:10:32Z)
• Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line [65.14099135546594]
  Recent test-time adaptation (TTA) methods drastically strengthen the ACL and AGL trends in models, even in shifts where models showed very weak correlations before. Our results show that by combining TTA with AGL-based estimation methods, we can estimate the OOD performance of models with high precision for a broader set of distribution shifts.
  arXiv  Detail & Related papers  (2023-10-07T23:21:25Z)
• HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression [69.36555801766762]
  We propose a hardware-aware tensor decomposition framework, dubbed HEAT, that enables efficient exploration of the exponential space of possible decompositions. We experimentally show that our hardware-aware factorized BERT variants reduce the energy-delay product by 5.7x with less than 1.1% accuracy loss.
  arXiv  Detail & Related papers  (2022-11-30T05:31:45Z)

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.