LiFTER turns future-link forecasting into a verifiable grounded computation and achieves competitive historical-negative forecasting and the highest macro explanation ac- curacy and deletion fidelity across four CTDG benchmarks.
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.
High-complexity operational environments require methods that detect and anticipate temporally distributed patterns rather than classify isolated events. This paper introduces TRACTA (Temporal Reasoning and Capability-Trajectory Analysis), a controlled synthetic benchmark for temporal structural reasoning in high-complexity event-driven systems, instantiated through Multi-Domain Operations (MDO)-like scenarios. The benchmark includes three tasks: early_warning, pattern_detection, and run_classification, and compares raw-event neural models, a contract-lite semantic baseline, and a neuro-symbolic configuration operating on semantically grounded trajectories. Results show that raw event-level learning remains informative, but learned temporal modeling over semantic capability and contextual direct-impact trajectories achieves the highest aggregate point estimates, with the largest margins on the temporal tasks. Ablation analysis indicates that capability dynamics, contextual impacts, and temporal structure contribute complementary information. Shortcut diagnostics indicate that the most direct cross-run global-identifier shortcut is controlled in the primary neural input view, while residual shallow signals remain. Overall, the findings support a bounded methodological conclusion: in controlled synthetic settings, semantically grounded trajectories provide an effective representation for temporal structural reasoning, supporting further investigation of semantic interfaces between event data, structured representations, and temporal learning.
Michael Romei de Socio, G. Pozzato, Alessio Merlo· 0 citations
Partially observable reinforcement learning requires deciding what to retain, retrieve, and forget over time. We introduce a neuro-symbolic meta-policy that learns which symbolic memory heuristic to apply at each decision point while keeping execution symbolic. Our setting uses temporal knowledge-graph memory in RoomKG, where hidden state and observations are represented as Resource Description Framework (RDF) graphs and memory is augmented with temporal RDF triple annotations. The model combines knowledge-graph encoding of memory contents with value heads for question answering, exploration, and forgetting, yielding a controller that is both adaptive and inspectable. This gives the work a direct Semantic Web grounding through RDF-based representation, annotation-compatible graph semantics, and graph-based symbolic operations over explicit memory state. On train/test room splits at long-term memory capacity of 512, the qualifier-aware StarE-GNN configuration achieves the best held-out performance among the compared symbolic, neural, and neuro-symbolic systems while preserving step-level traceability of memory-management decisions.
Taewoon Kim, Vincent François-Lavet, Michael Cochez· 0 citations
This work formalizes explanations as Halpern-Pearl actual causes, modeling input dependencies using Boolean Structural Causal Models (SCMs), and compute HP causes by applying bound propagation and branch-and-bound techniques, while providing formal guarantees of completeness and minimality.
Jannick Strobel, Muqsit Azeem, Stefan Leue· 0 citations
Temporal Knowledge Graphs (TKGs) record how facts evolve over time, but forecasting future events on a TKG remains difficult for three reasons: (i) long-range temporal dependencies are hard to encode; (ii) events on different chains mutually excite or inhibit one another in ways that snapshot-level models cannot express; and (iii) inter-arrival times are heavy-tailed and statistically sparse, so deterministic time predictors are unreliable. We address these three issues with a single framework, the \textbf{Group Attention Neural Hawkes Process (GAttNHP)}, built around three matched components. First, a self-attention encoder casts each subject--relation chain as a continuous-time point process and captures the lingering excitation of distant history. Second, a semantic soft-grouping module turns globally learnable Hawkes priors into an analytical cross-attention mask, so chains share excitation patterns through their latent group memberships rather than through exhaustive pairwise computation. Third, a Non-Crossing Quantile (NCQ) regression head replaces mean-based time prediction, providing calibrated, monotonically ordered quantile estimates that remain stable under heavy-tailed inter-arrival distributions. On six benchmark TKG datasets, GAttNHP improves over state-of-the-art baselines on both entity prediction and time prediction, and ablations confirm that its largest gains arise on the long-tail event chains where existing models fail most severely.
Xiangni Tian, Kaixian Yu, Runpeng Dai et al.· 0 citations
The Temporal-Weighted Transfer Network (TWTNET), a novel reasoning model that jointly leverages statistical modeling and historical information transfer, is proposed, which achieves more robust and interpretable extrapolative reasoning.
Hongyu Hao, Yifan Zhang, Xinru Zhao et al.· ACM Transactions on Intellig...· 0 citations
Interpreting predictions of temporal graph neural networks (TGNNs) is challenging: structural patterns are entangled with temporal dynamics and node-level activity. Existing methods often overemphasize frequent or recent interactions, producing explanations that conflate structural influence with temporal or behavioral confounding and are not grounded by motif-level evidence. We propose CATGX, a confounder-aware framework for explaining temporal graph predictions through motif-level reasoning. CATGX models temporal interaction mechanisms as motif occurrences, and explicitly treats temporal context and entity activity as observed confounders. By abstracting causal factors into temporal motif, context, and entity codebooks, CATGX applies an adjustment-inspired scoring scheme that compares motif-level influence to isolate structural contributions that persist across comparable conditions. To support fast explanation generation, CATGX integrates graph approximate nearest neighbor (ANN) sampling strategy as an unbiased motif occurrence statistics estimator, which preserves unbiased estimation through importance weighting. The entire pipeline operates in a training-free, model-agnostic manner and achieves bounded, low polynomial-time cost. Experiments demonstrate that CATGX strikes a good balance to generate explanations that are faithful, grounded and confounder-aware, and outperform existing TGNN explainers in efficiency with 83x speed up.
Mingjian Lu, Hieu M. Vu, Vu K Le et al.· Proceedings of the 32nd ACM...· 0 citations
