arXiv:2608. 12435v1 Announce Type: new Abstract: Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length.
MambaTG is a new framework for future link prediction on temporal graphs that addresses both repeated and unseen edge prediction. It leverages two complementary signals: the historical-sequence evolution of a node’s interactions and the compatibility between a candidate edge and the node’s evolving history. By using a candidate-aware Mamba architecture, the model captures ordered interaction dynamics and adapts state transitions to different candidates, achieving strong performance across 13 datasets while remaining computationally efficient.
HERO is a heterogeneous continual graph learning framework that preserves historical knowledge at both structural and semantic levels while adapting to new tasks. It uses DiSCo to select representative target nodes and reconstruct compact heterogeneous contexts, and applies multi-level knowledge distillation to align task-conditioned predictions with semantic responses. Experiments on four datasets with three HGNN backbones show HERO achieves best or tied-best average performance while maintaining competitive forgetting.
Future link prediction on temporal graphs involves both repeated interactions between previously connected node pairs and first-time interactions between pairs with no prior interaction. While repeate...
TTGBench is a new benchmark for temporal graph learning that evaluates both structural evolution and semantic drift in text‑attributed graphs. It includes six real‑world, text‑rich datasets with dual volatility and supports multi‑class and multi‑label temporal node classification, addressing gaps left by existing benchmarks. A comprehensive evaluation of 17 state‑of‑the‑art methods shows a clear divide: TGNNs excel at structural prediction but struggle with semantic tracking, while LLM‑based models perform better on semantic tasks but lag in structural prediction.
CacheDyG introduces a cache‑refine framework that decouples temporal propagation from parameter updates in dynamic graph neural networks. By storing graph‑aware node‑time representations in non‑trainable buffers and updating only a lightweight refiner, residual gate, and link predictor during training, it reduces repeated recomputation of historical structures. Experiments on five benchmarks show that CacheDyG uses fewer trainable parameters, runs faster, and achieves competitive or better predictive performance compared to existing baselines.
arXiv:2607. 18412v1 Announce Type: new Abstract: Dynamic graph learning aims to capture evolving structural and semantic patterns in real-world systems, such as fraud detection and recommender systems.
arXiv:2504. 07337v2 Announce Type: replace Abstract: Aggregating temporal signals from historic interactions is a key step in future link prediction on dynamic graphs.
SiST‑GNN introduces a simultaneous spatial‑temporal message‑passing framework for dynamic graph neural networks, fusing per‑node temporal embeddings with spatial aggregation in a single operation. By maintaining a recurrent hidden state per node and treating it as a cross‑time edge, the model jointly reasons over topology and evolution. Experiments on link‑prediction and node‑classification benchmarks show significant improvements over prior methods, achieving up to 158% gains in live‑update link prediction and outperforming discrete‑time baselines by 7–23% in dynamic node classification.
arXiv:2608. 19652v1 Announce Type: new Abstract: As LLM-based agents are deployed for longer and higher-stakes tasks, their memory systems continue to have crucial gaps.
arXiv:2610.34833v1 Announce Type: cross Abstract: Natural intelligence learns from a continuous stream of sensorimotor experience: data can arrive at high bandwidth, and behavior adapts to feedback a...
The paper introduces QGMem, a memory framework for conversational agents that organizes dialogue history into event-indexed atomic units and consolidates related units into dynamic memory traces. When a query is posed, QGMem retrieves complementary candidate memories, reranks them to form a compact working memory, and represents this working memory as a local graph to expose relational dependencies. Experiments on six benchmarks demonstrate consistent improvements in retrieval, multi‑hop evidence composition, conflict resolution, and ultra‑long dialogue reasoning while keeping context size and inference cost moderate.