StruMPL: Multi-task Dense Regression under Disjoint Partial Supervision and MNAR Labels

• URL: http://arxiv.org/abs/2605.19931v1
• Date: Tue, 19 May 2026 14:51:12 GMT
• Title: StruMPL: Multi-task Dense Regression under Disjoint Partial Supervision and MNAR Labels
• Abstract summary: Estimating forest aboveground biomass (AGB) from Earth observation combines two structurally incompatible label sources.<n>We formalise this as multi-task dense regression under heterogeneous disjoint partial supervision with MNAR labels and inter-task physical constraints.<n>We show analytically and empirically that both are necessary for joint optimisation to recover IPW-weighted stationary points while keeping the loss bounded.
• Score: 0.25241093712112367
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Estimating forest aboveground biomass (AGB) from Earth observation combines two structurally incompatible label sources: spaceborne lidar provides canopy structure at millions of locations but no biomass estimate, and ground-based plots provide biomass at thousands of biased locations but no metrics of structure. No single training sample carries labels for all target variables, plot labels are missing not at random (MNAR), and biomass is linked to the structural variables by known but biome-specific allometric laws. We formalise this as multi-task dense regression under heterogeneous disjoint partial supervision with MNAR labels and inter-task physical constraints, and propose StruMPL to address it jointly. A shared encoder feeds per-variable regression, imputation, and propensity heads for spatial MNAR correction, and a learnable physics module that evaluates the inter-task constraint on the model's own predictions at every pixel. The supervised loss uses an Augmented IPW (AIPW) pseudo-outcome with stop-gradients on the propensity and on the imputation baseline; we show analytically and empirically that both are necessary for joint optimisation to recover IPW-weighted stationary points while keeping the loss bounded. On two ecologically distinct biomes, StruMPL outperforms ablation variants and the closest published method on AGB RMSE and bias, with a stratified analysis showing AIPW reduces high-AGB bias by ~54%.

Related papers

• Transferable Above-Ground Biomass (AGB) Estimation Model from Multi-Sensor Data with Sparse Field Calibration [0.0]
  This paper presents an operational framework centered on a single globally trained convolutional neural network (CNN)<n>The framework applies a small number of local field plots to fit a scale-and-bias correction that aligns the global prediction with ground truth in each region.<n>On held-out validation the global GEDI-based model achieved R2 approximately 0.78 and RMSE approximately 22 Mg/ha.
  arXiv  Detail & Related papers  (2026-08-12T04:36:26Z)
• BioM-JEPA: joint-embedding prediction of graph-connected gene blocks in single cells [64.21963170814706]
  BioM-JEPA predicts aggregate representations of graph-connected gene blocks.<n>A student network infers each target-block representation from the remaining genes in a cell.<n>Across CellBench tasks, BioM-JEPA embeddings retained expression, pathway and neighbourhood information.
  arXiv  Detail & Related papers  (2026-08-06T11:58:29Z)
• scHelix: Asymmetric Dual-Stream Integration via Explicit Gene-Level Disentanglement [84.88065404629079]
  scHelix is a dataset-adaptive framework that fundamentally changes how features are processed.<n> scHelix utilizes a dual-stream sparse diffusion encoder equipped with stop-gradient graph caching.<n> scHelix outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-18T15:55:13Z)
• SEED: Targeted Data Selection by Weighted Independent Set [76.92528228676969]
  We develop a robust and scalable data selection pipeline dubbed SEED.<n>SEED consistently outperforms state-of-the-art methods on instruction tuning, visual instruction tuning, and semantic segmentation.
  arXiv  Detail & Related papers  (2026-05-15T07:26:54Z)
• Rethinking Molecular OOD Generalization via Target-Aware Source Selection [10.102858221967791]
  SCOPE-BENCH is a benchmark built on cluster-level partitioning in an explicit physicochemical descriptor space.<n>POMA is a framework that formulates knowledge transfer as a retrieve-compose-adapt pipeline.<n> Evaluations show that prediction errors of state-of-the-art 3D molecular models surge by up to 8.0x on SCOPE-BENCH with a mean of 5.9x.
  arXiv  Detail & Related papers  (2026-05-13T16:09:46Z)
• Ecologically-Constrained Task Arithmetic for Multi-Taxa Bioacoustic Classifiers Without Shared Data [6.033831199709592]
  Training data for bioacoustics is scattered across taxa, regions, and institutions.<n>We show that independently fine-tuned BEATs encoders can be composed into a unified 661-species classifier.
  arXiv  Detail & Related papers  (2026-05-05T16:10:02Z)
• Direct Estimation of Tree Volume and Aboveground Biomass Using Deep Regression with Synthetic Lidar Data [4.588276431770691]
  estimation of forest biomass is crucial for monitoring carbon sequestration and informing climate change mitigation strategies.<n>Existing methods often rely on allometric models, which estimate individual tree biomass by relating it to measurable biophysical parameters, e.g., trunk diameter and height.<n>This study proposes a direct approach that leverages synthetic point cloud data to train a deep regression network, which is then applied to real point clouds for plot-level wood volume estimation.
  arXiv  Detail & Related papers  (2026-03-04T23:56:41Z)
• Calibrated Probabilistic Interpolation for GEDI Biomass [0.0]
  We introduce Attentive Neural Processes (ANPs), a probabilistic meta-learning framework that explicitly conditions predictions on local observation sets.<n>We validate this approach across five distinct biomes ranging from Tropical Amazonian forests to Boreal and Alpine ecosystems.<n>This work provides a scalable, theoretically rigorous alternative to ensemble variance for continental scale earth observation.
  arXiv  Detail & Related papers  (2026-01-23T15:35:33Z)
• Unlasting: Unpaired Single-Cell Multi-Perturbation Estimation by Dual Conditional Diffusion Implicit Bridges [68.98973318553983]
  We propose a framework based on Dual Diffusion Implicit Bridges (DDIB) to learn the mapping between different data distributions.<n>We integrate gene regulatory network (GRN) information to propagate perturbation signals in a biologically meaningful way.<n>We also incorporate a masking mechanism to predict silent genes, improving the quality of generated profiles.
  arXiv  Detail & Related papers  (2025-06-26T09:05:38Z)
• How Does Pseudo-Labeling Affect the Generalization Error of the Semi-Supervised Gibbs Algorithm? [73.80001705134147]
  We provide an exact characterization of the expected generalization error (gen-error) for semi-supervised learning (SSL) with pseudo-labeling via the Gibbs algorithm. The gen-error is expressed in terms of the symmetrized KL information between the output hypothesis, the pseudo-labeled dataset, and the labeled dataset.
  arXiv  Detail & Related papers  (2022-10-15T04:11:56Z)
• Improving Molecular Representation Learning with Metric Learning-enhanced Optimal Transport [49.237577649802034]
  We develop a novel optimal transport-based algorithm termed MROT to enhance their generalization capability for molecular regression problems. MROT significantly outperforms state-of-the-art models, showing promising potential in accelerating the discovery of new substances.
  arXiv  Detail & Related papers  (2022-02-13T04:56:18Z)
• Semantic Change Detection with Asymmetric Siamese Networks [71.28665116793138]
  Given two aerial images, semantic change detection aims to locate the land-cover variations and identify their change types with pixel-wise boundaries. This problem is vital in many earth vision related tasks, such as precise urban planning and natural resource management. We present an asymmetric siamese network (ASN) to locate and identify semantic changes through feature pairs obtained from modules of widely different structures.
  arXiv  Detail & Related papers  (2020-10-12T13:26:30Z)

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.