Towards Universal Neural Inference

• URL: http://arxiv.org/abs/2508.09100v1
• Date: Tue, 12 Aug 2025 17:26:48 GMT
• Title: Towards Universal Neural Inference
• Authors: Shreyas Bhat Brahmavar, Yang Li, Junier Oliva,
• Abstract summary: ASPIRE is a Universal Neural Inference model for semantic reasoning and prediction over structured data.<n>It ingests arbitrary sets of feature--value pairs, align semantics across disjoint tables, and make predictions for any specified target.<n>ASPIRE naturally supports cost-aware active feature acquisition in an open-world setting.
• Score: 12.704979719123637
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real-world data often appears in diverse, disjoint forms -- with varying schemas, inconsistent semantics, and no fixed feature ordering -- making it challenging to build general-purpose models that can leverage information across datasets. We introduce ASPIRE, Arbitrary Set-based Permutation-Invariant Reasoning Engine, a Universal Neural Inference model for semantic reasoning and prediction over heterogeneous structured data. ASPIRE combines a permutation-invariant, set-based Transformer with a semantic grounding module that incorporates natural language descriptions, dataset metadata, and in-context examples to learn cross-dataset feature dependencies. This architecture allows ASPIRE to ingest arbitrary sets of feature--value pairs and support examples, align semantics across disjoint tables, and make predictions for any specified target. Once trained, ASPIRE generalizes to new inference tasks without additional tuning. In addition to delivering strong results across diverse benchmarks, ASPIRE naturally supports cost-aware active feature acquisition in an open-world setting, selecting informative features under test-time budget constraints for an arbitrary unseen dataset. These capabilities position ASPIRE as a step toward truly universal, semantics-aware inference over structured data.

Related papers

• From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detection [89.52759572485276]
  ARC is a few-shot generalist GAD method that leverages in-context learning and requires only a few labeled normal samples at inference time.<n> ARC and ARC_zero effectively detect anomalies, exhibit strong generalization ability, and perform efficiently under few-shot and zero-shot settings.
  arXiv  Detail & Related papers  (2026-02-21T10:59:00Z)
• OmniStruct: Universal Text-to-Structure Generation across Diverse Schemas [57.49565459553627]
  We introduce OmniStruct, a benchmark for assessing Large Language Models' capabilities on text-to-structure tasks.<n>We collect high-quality training data via synthetic task generation to facilitate the development of efficient text-to-structure models.<n>Our experiments demonstrate the possibility of fine-tuning much smaller models on synthetic data into universal structured generation models.
  arXiv  Detail & Related papers  (2025-11-23T08:18:12Z)
• Enhancing Self-Supervised Learning with Semantic Pairs A New Dataset and Empirical Study [2.4405762029252465]
  Instance discrimination is a self-supervised representation learning paradigm wherein individual instances within a dataset are treated as distinct classes.<n>We provide the technical foundation for leveraging semantic pairs to enhance the generalizability of the model's representation.
  arXiv  Detail & Related papers  (2025-10-09T18:31:55Z)
• DaSAThco: Data-Aware SAT Heuristics Combinations Optimization via Large Language Models [2.9789407216680286]
  We introduce DaSAThco, a framework that learns a generalizable mapping from instance features to tailored ensembles.<n>Our framework uses a Large Language Model, guided by systematically defined Problem Archetypes, to generate a diverse portfolio of specialized ensembles and subsequently learns an adaptive selection mechanism to form the final mapping.
  arXiv  Detail & Related papers  (2025-09-16T02:58:50Z)
• Self-supervised Latent Space Optimization with Nebula Variational Coding [87.20343320266215]
  This paper proposes a variational inference model which leads to a clustered embedding.<n>We introduce additional variables in the latent space, called textbfnebula anchors, that guide the latent variables to form clusters during training.<n>Since each latent feature can be labeled with the closest anchor, we also propose to apply metric learning in a self-supervised way to make the separation between clusters more explicit.
  arXiv  Detail & Related papers  (2025-06-02T08:13:32Z)
• Make Still Further Progress: Chain of Thoughts for Tabular Data Leaderboard [27.224577475861214]
  Tabular data, a fundamental data format in machine learning, is predominantly utilized in competitions and real-world applications.<n>We propose an in-context ensemble framework for tabular prediction that leverages large language models.<n>Our method constructs a context around each test instance using its nearest neighbors and the predictions from a pool of external models.
  arXiv  Detail & Related papers  (2025-05-19T17:52:58Z)
• Spatial-Temporal-Spectral Unified Modeling for Remote Sensing Dense Prediction [20.1863553357121]
  Current deep learning architectures for remote sensing are fundamentally rigid.<n>We introduce the Spatial-Temporal-Spectral Unified Network (STSUN) for unified modeling.<n> STSUN can adapt to input and output data with arbitrary spatial sizes, temporal lengths, and spectral bands.<n>It unifies various dense prediction tasks and diverse semantic class predictions.
  arXiv  Detail & Related papers  (2025-05-18T07:39:17Z)
• Meta-Statistical Learning: Supervised Learning of Statistical Inference [59.463430294611626]
  This work demonstrates that the tools and principles driving the success of large language models (LLMs) can be repurposed to tackle distribution-level tasks.<n>We propose meta-statistical learning, a framework inspired by multi-instance learning that reformulates statistical inference tasks as supervised learning problems.
  arXiv  Detail & Related papers  (2025-02-17T18:04:39Z)
• TARGA: Targeted Synthetic Data Generation for Practical Reasoning over Structured Data [9.390415313514762]
  TARGA is a framework that generates high-relevance synthetic data without manual annotation.<n>It substantially outperforms existing non-fine-tuned methods that utilize close-sourced model.<n>It exhibits superior sample efficiency, robustness, and generalization capabilities under non-I.I.D. settings.
  arXiv  Detail & Related papers  (2024-12-27T09:16:39Z)
• Structural Entropy Guided Probabilistic Coding [52.01765333755793]
  We propose a novel structural entropy-guided probabilistic coding model, named SEPC.<n>We incorporate the relationship between latent variables into the optimization by proposing a structural entropy regularization loss.<n> Experimental results across 12 natural language understanding tasks, including both classification and regression tasks, demonstrate the superior performance of SEPC.
  arXiv  Detail & Related papers  (2024-12-12T00:37:53Z)
• Learning Prototype-oriented Set Representations for Meta-Learning [85.19407183975802]
  Learning from set-structured data is a fundamental problem that has recently attracted increasing attention. This paper provides a novel optimal transport based way to improve existing summary networks. We further instantiate it to the cases of few-shot classification and implicit meta generative modeling.
  arXiv  Detail & Related papers  (2021-10-18T09:49:05Z)
• Set Representation Learning with Generalized Sliced-Wasserstein Embeddings [22.845403993200932]
  We propose a geometrically-interpretable framework for learning representations from set-structured data. In particular, we treat elements of a set as samples from a probability measure and propose an exact Euclidean embedding for Generalized Sliced Wasserstein. We evaluate our proposed framework on multiple supervised and unsupervised set learning tasks and demonstrate its superiority over state-of-the-art set representation learning approaches.
  arXiv  Detail & Related papers  (2021-03-05T19:00:34Z)

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.