Architecture-Agnostic Curriculum Learning for Document Understanding: Empirical Evidence from Text-Only and Multimodal

• URL: http://arxiv.org/abs/2602.21225v1
• Date: Mon, 02 Feb 2026 10:09:26 GMT
• Title: Architecture-Agnostic Curriculum Learning for Document Understanding: Empirical Evidence from Text-Only and Multimodal
• Abstract summary: We investigate whether progressive data scheduling yields consistent efficiency gains across document understanding models.<n>We establish that this schedule reduces wall-clock training time by approximately 33%, commensurate with the reduction from 6.67 to 10.0 effective epoch-reductions of data.
• Score: 13.329839705160927
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We investigate whether progressive data scheduling -- a curriculum learning strategy that incrementally increases training data exposure (33\%$\rightarrow$67\%$\rightarrow$100\%) -- yields consistent efficiency gains across architecturally distinct document understanding models. By evaluating BERT (text-only, 110M parameters) and LayoutLMv3 (multimodal, 126M parameters) on the FUNSD and CORD benchmarks, we establish that this schedule reduces wall-clock training time by approximately 33\%, commensurate with the reduction from 6.67 to 10.0 effective epoch-equivalents of data. To isolate curriculum effects from compute reduction, we introduce matched-compute baselines (Standard-7) that control for total gradient updates. On the FUNSD dataset, the curriculum significantly outperforms the matched-compute baseline for BERT ($Δ$F1 = +0.023, $p=0.022$, $d_z=3.83$), constituting evidence for a genuine scheduling benefit in capacity-constrained models. In contrast, no analogous benefit is observed for LayoutLMv3 ($p=0.621$), whose multimodal representations provide sufficient inductive bias. On the CORD dataset, all conditions converge to equivalent F1 scores ($\geq$0.947) irrespective of scheduling, indicating a performance ceiling. Schedule ablations comparing progressive, two-phase, reverse, and random pacing confirm that the efficiency gain derives from reduced data volume rather than ordering. Taken together, these findings demonstrate that progressive scheduling is a reliable compute-reduction strategy across model families, with curriculum-specific benefits contingent on the interaction between model capacity and task complexity.

Related papers

• Gradient-Based Data Valuation Improves Curriculum Learning for Game-Theoretic Motion Planning [9.553350856191743]
  gradient-based data valuation produces curriculum orderings that significantly outperform metadata-based subsets for training gametheoretic motion planners.<n> gradient-based data valuation as a practical tool for improving sample efficiency in game-theoretic planning.
  arXiv  Detail & Related papers  (2026-04-01T02:17:27Z)
• Estimating Time Series Foundation Model Transferability via In-Context Learning [74.65355820906355]
  Time series foundation models (TSFMs) offer strong zero-shot forecasting via large-scale pre-training.<n>Fine-tuning remains critical for boosting performance in domains with limited public data.<n>We introduce TimeTic, a transferability estimation framework that recasts model selection as an in-context-learning problem.
  arXiv  Detail & Related papers  (2025-09-28T07:07:13Z)
• FedTeddi: Temporal Drift and Divergence Aware Scheduling for Timely Federated Edge Learning [12.104759384825705]
  Federated edge learning (FEEL) enables collaborative model training across distributed clients over wireless networks without exposing raw data.<n>A critical challenge is how to adapt models in a timely yet efficient manner to such evolving data.<n>We propose FedTeddi, a temporal-drift-and-divergence-aware scheduling algorithm that facilitates fast convergence of FEEL.
  arXiv  Detail & Related papers  (2025-09-09T02:33:48Z)
• SPaRFT: Self-Paced Reinforcement Fine-Tuning for Large Language Models [51.74498855100541]
  Large language models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL)<n>We propose textbfSPaRFT, a self-paced learning framework that enables efficient learning based on the capability of the model being trained.
  arXiv  Detail & Related papers  (2025-08-07T03:50:48Z)
• Is Architectural Complexity Overrated? Competitive and Interpretable Knowledge Graph Completion with RelatE [6.959701672059059]
  RelatE is an interpretable and modular method that efficiently integrates dual representations for entities and relations.<n>It achieves competitive or superior performance on standard benchmarks.<n>Perturbation studies demonstrate improved robustness, with MRR reduced by up to 61% relative to TransE and by up to 19% compared to RotatE.
  arXiv  Detail & Related papers  (2025-05-25T04:36:52Z)
• Mastering Collaborative Multi-modal Data Selection: A Focus on Informativeness, Uniqueness, and Representativeness [63.484378941471114]
  We propose a collaborative framework, DataTailor, which leverages three key principles--informativeness, uniqueness, and representativeness--for effective data selection.<n>Experiments on various benchmarks demonstrate that DataTailor achieves 101.3% of the performance of full-data fine-tuning with only 15% of the data.
  arXiv  Detail & Related papers  (2024-12-09T08:36:10Z)
• Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular Data [39.40116554523575]
  We present Drift-Resilient TabPFN, a fresh approach based on In-Context Learning with a Prior-Data Fitted Network. It learns to approximate Bayesian inference on synthetic datasets drawn from a prior. It improves accuracy from 0.688 to 0.744 and ROC AUC from 0.786 to 0.832 while maintaining stronger calibration.
  arXiv  Detail & Related papers  (2024-11-15T23:49:23Z)
• The Surprising Effectiveness of Test-Time Training for Few-Shot Learning [59.309477460893916]
  Language models (LMs) have shown impressive performance on tasks within their training distribution, but often struggle with structurally novel tasks.<n>We investigate the effectiveness of test-time training (TTT) as a mechanism for improving LMs' reasoning and few-shot learning capabilities.<n>Our findings highlight the limitations of in-context learning for novel tasks and demonstrate the potential of test-time training to enhance language model adaptability.
  arXiv  Detail & Related papers  (2024-11-11T18:59:45Z)
• DELIFT: Data Efficient Language model Instruction Fine Tuning [13.538140114667772]
  We introduce DELIFT, a novel algorithm that systematically optimize data selection across the three key stages of fine-tuning.<n>Experiments across various tasks and model scales demonstrate that DELIFT can reduce the fine-tuning data size by up to 70% without compromising performance.
  arXiv  Detail & Related papers  (2024-11-07T04:38:29Z)
• Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping [53.454408491386886]
  bootstrapping self-alignment markedly surpasses the single-round approach. We propose Step-On-Feet Tuning (SOFT) which leverages model's continuously enhanced few-shot ability to boost zero or one-shot performance. Based on easy-to-hard training recipe, we propose SOFT+ which further boost self-alignment's performance.
  arXiv  Detail & Related papers  (2024-02-12T12:30:42Z)
• Exploring Learning Complexity for Efficient Downstream Dataset Pruning [8.990878450631596]
  Existing dataset pruning methods require training on the entire dataset.<n>We propose a straightforward, novel, and training-free hardness score named Distorting-based Learning Complexity (DLC)<n>Our method is motivated by the observation that easy samples learned faster can also be learned with fewer parameters.
  arXiv  Detail & Related papers  (2024-02-08T02:29:33Z)
• 90% F1 Score in Relational Triple Extraction: Is it Real ? [5.188158867781318]
  Extracting relational triples from text is a crucial task for constructing knowledge bases. Recent advancements in joint entity and relation extraction models have demonstrated remarkable F1 scores. We present a benchmark study of state-of-the-art joint entity and relation extraction models under a more realistic setting.
  arXiv  Detail & Related papers  (2023-02-20T10:30:16Z)
• Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training [110.79400526706081]
  Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage limit their generalization. Previous compression algorithms usually start from the pre-trained dense models and only focus on efficient inference. This paper proposes an end-to-end efficient training framework from three sparse perspectives, dubbed Tri-Level E-ViT.
  arXiv  Detail & Related papers  (2022-11-19T21:15:47Z)

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.