← Back to all news
arXiv Machine Learning By Yue Hou, Ruomei Liu, Yingke Su, Junran Wu, Ke Xu

Efficient Memory Crystallization for Graph Learning under Non-Stationary Distribution Shifts

Read the original on arXiv Machine Learning →

Efficient Memory Crystallization (EMC) is a training‑free, test‑time framework that transforms each incoming graph domain into a compact, semantically faithful memory via a closed‑form distribution‑matching solution. By eliminating the need for auxiliary generative modules, EMC reduces redundant domain information and models inter‑domain dependencies through state‑evolving memories, yielding a tighter generalization error bound. Experiments show EMC outperforms state‑of‑the‑art baselines on non‑stationary graph data, cutting average runtime by 87.4% and GPU memory usage by 92.4% compared to a recent competitor.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Aug 31

Temporal Memory-Aware Online Test-Time Adaptation on Dynamic Graphs

The paper introduces DGOTTA, a framework for temporal memory‑aware online test‑time adaptation on dynamic graphs. DGOTTA comprises three modules: temporal‑aware augmentation to diversify test graphs, memory‑aware model prediction to mitigate catastrophic forgetting, and consistency‑guided online adaptation to enforce temporal alignment and smoothness. Experiments on three real‑world datasets and four DGNN backbones show that DGOTTA improves generalization under diverse distribution shifts and across multiple model architectures.

By Bo Li, Xin Zheng, Ming Jin, Can Wang, Shirui Pan
safety
More like this →
arXiv Machine Learning
Oct 23

Graph Memory Transformer (GMT)

The paper introduces the Graph Memory Transformer (GMT), a decoder‑only language model that replaces the traditional Feed‑Forward Network sublayer with an explicit learned memory graph. In GMT, token representations are routed through a bank of centroids linked by a directed transition matrix, using gravitational source routing and token‑conditioned target selection to produce gated displacements instead of retrieved values. The resulting model contains 82.2 M parameters, trains stably, and offers direct inspection of centroid usage and transition structure, though it slightly lags a larger GPT‑style baseline in validation loss and perplexity.

By Nicola Zanarini, Niccol\`o Ferrari, Evelina Lamma
llmsbenchmarkssafety
More like this →