LiFTER: A Grounded Neuro-Symbolic Microscope for Continuous-Time Dynamic Graph Forecasting

• URL: http://arxiv.org/abs/2608.06765v1
• Date: Fri, 07 Aug 2026 03:39:09 GMT
• Title: LiFTER: A Grounded Neuro-Symbolic Microscope for Continuous-Time Dynamic Graph Forecasting
• Abstract summary: Continuous-time dynamic graph models predict future links by compressing past interactions into neural states.<n>LiFTER is a neuro-symbolic predictor that preserves observed interactions as grounded temporal facts.<n>LiFTER achieves competitive historical-negative forecasting and the highest macro explanation ac- curacy and deletion fidelity.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continuous-time dynamic graph models predict future links by compressing past interactions into neural states. Although effective for forecasting, this computation obscures which entities are shared across events and how temporal patterns contribute to a prediction. We treat this gap as a property of the predictive architecture rather than a problem to be addressed after prediction. Link-Fact Temporal Rule Inducer (LiFTER) is a neuro-symbolic predictor that preserves observed interactions as grounded temporal facts and applies executable tempo- ral rules to pre-query facts. Each score is a signed sum of rule exe- cutions whose historical facts, entity bindings, and temporal order are explicitly satisfied. The evidence and rules responsible for a prediction can therefore be inspected, independently recomputed, and intervened upon. Across four CTDG benchmarks, LiFTER achieves competitive historical-negative forecasting and the highest macro explanation ac- curacy and deletion fidelity. The same architecture also serves as a microscope that separates the contributions of recurrence, history po- sition, and transition across datasets and traces them to individual facts. Independent execution reconstructs all logits for 19,664 test predictions with a maximum error of 0.0000131. LiFTER turns future-link forecasting into a verifiable grounded computation.

Related papers

• Do Generative Models Keep Time? A Time-Aware Evaluation of Synthetic Sequential Tabular Data [28.948173366251286]
  We present a taxonomy-guided evaluation protocol for temporal fidelity.<n>We apply the protocol to eight generative models across thirteen datasets spanning six domains.
  arXiv  Detail & Related papers  (2026-07-17T03:59:35Z)
• Causal Longitudinal Prior-Fitted Networks for Counterfactual Outcome Prediction [0.0]
  We introduce Causal Longitudinal Prior-Fitted Networks (CausalLongPFN) for time-series causal inference in longitudinal treatment-response data.<n>CausalLongPFN is a prior-fitted network for time-series causal inference in longitudinal treatment-response data and zero-shot in-context counterfactual outcome prediction.<n>We evaluate the model on branchable cancer, HIV, and warfarin benchmarks with ground-truth counterfactual labels, and on factual-only rolling-origin prediction in MIMIC-III ICU trajectories.
  arXiv  Detail & Related papers  (2026-06-04T07:26:40Z)
• Generating Causal Temporal Interaction Graphs for Counterfactual Validation of Temporal Link Prediction [7.925229590936017]
  We generate causal temporal interaction graphs (CTIGs) with known ground-truth causal structure.<n>To compare causal models, we propose a distance metric based on cross-model predictive error.<n>Our framework provides a foundation for causality benchmarking.
  arXiv  Detail & Related papers  (2026-02-02T14:36:18Z)
• Weak Relation Enforcement for Kinematic-Informed Long-Term Stock Prediction with Artificial Neural Networks [0.0]
  We propose loss function week enforcement of the velocity relations between time-series points in the Kinematic-Informed artificial Neural Networks (KINN) for long-term stock prediction.
  arXiv  Detail & Related papers  (2025-11-13T17:00:51Z)
• Revisiting Multivariate Time Series Forecasting with Missing Values [65.30332997607141]
  Missing values are common in real-world time series.<n>Current approaches have developed an imputation-then-prediction framework that uses imputation modules to fill in missing values, followed by forecasting on the imputed data.<n>This framework overlooks a critical issue: there is no ground truth for the missing values, making the imputation process susceptible to errors that can degrade prediction accuracy.<n>We introduce Consistency-Regularized Information Bottleneck (CRIB), a novel framework built on the Information Bottleneck principle.
  arXiv  Detail & Related papers  (2025-09-27T20:57:48Z)
• Relational Conformal Prediction for Correlated Time Series [56.59852921638328]
  We address the problem of uncertainty quantification in time series by exploiting correlated sequences.<n>We propose a novel distribution-free approach based on conformal prediction framework and quantile regression.<n>Our approach provides accurate coverage and achieves state-of-the-art uncertainty quantification in relevant benchmarks.
  arXiv  Detail & Related papers  (2025-02-13T16:12:17Z)
• HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention [76.37139809114274]
  HPNet is a novel dynamic trajectory forecasting method. We propose a Historical Prediction Attention module to automatically encode the dynamic relationship between successive predictions. Our code is available at https://github.com/XiaolongTang23/HPNet.
  arXiv  Detail & Related papers  (2024-04-09T14:42:31Z)
• NeuSTIP: A Novel Neuro-Symbolic Model for Link and Time Prediction in Temporal Knowledge Graphs [13.442923127130806]
  We propose a novel temporal neuro-symbolic model, NeuSTIP, that performs link prediction and time interval prediction in a temporal knowledge graph. NeuSTIP learns temporal rules in the presence of the Allen predicates that ensure the temporal consistency between neighboring predicates. Our empirical evaluation on two time interval based datasets suggests that our model outperforms state-of-the-art models for both link prediction and the time interval prediction task.
  arXiv  Detail & Related papers  (2023-05-15T13:46:34Z)
• Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction [60.60223171143206]
  Trajectory prediction is a crucial undertaking in understanding entity movement or human behavior from observed sequences. Current methods often assume that the observed sequences are complete while ignoring the potential for missing values. This paper presents a unified framework, the Graph-based Conditional Variational Recurrent Neural Network (GC-VRNN), which can perform trajectory imputation and prediction simultaneously.
  arXiv  Detail & Related papers  (2023-03-28T14:27:27Z)
• Predicting Temporal Sets with Deep Neural Networks [50.53727580527024]
  We propose an integrated solution based on the deep neural networks for temporal sets prediction. A unique perspective is to learn element relationship by constructing set-level co-occurrence graph. We design an attention-based module to adaptively learn the temporal dependency of elements and sets.
  arXiv  Detail & Related papers  (2020-06-20T03:29:02Z)
• Ambiguity in Sequential Data: Predicting Uncertain Futures with Recurrent Models [110.82452096672182]
  We propose an extension of the Multiple Hypothesis Prediction (MHP) model to handle ambiguous predictions with sequential data. We also introduce a novel metric for ambiguous problems, which is better suited to account for uncertainties.
  arXiv  Detail & Related papers  (2020-03-10T09:15:42Z)

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.