---
title: "CTDG-SSM Beats Top Graph AI Models Using One-Tenth the Parameters"
subtitle: "CTDG-SSM fuses HiPPO memory with graph Laplacian polynomials to achieve state-of-the-art on dynamic link prediction with 10x fewer parameters than competitors"
url: "https://alphasignal.ai/news/ctdg-ssm-beats-top-graph-ai-models-using-one-tenth-the-parameters"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-06-03T00:00:00.000Z"
updated: "2026-06-11T02:41:24.590Z"
type: "Paper"
topics:
  - "Llms"
  - "Benchmarks"
subtopics:
  - "Long Context"
  - "Vision Language"
upvotes: 2139
source_url: "https://arxiv.org/abs/2606.04672"
comments: 0
truncated: true
---

# CTDG-SSM Beats Top Graph AI Models Using One-Tenth the Parameters

> CTDG-SSM fuses HiPPO memory with graph Laplacian polynomials to achieve state-of-the-art on dynamic link prediction with 10x fewer parameters than competitors

Most real-world networks are not static. Friendships form and fade, financial transactions flow, students engage with course content at irregular intervals. Modeling these systems as **continuous-time dynamic graphs (CTDGs)** \-- where each interaction is a timestamped event rather than a snapshot -- gives far richer signal than the traditional approach of slicing time into discrete windows. But getting a neural network to actually learn from that richness has been stubbornly hard, especially when the patterns that matter span long time horizons and multiple hops across the graph. A new paper, ["Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models"](https://arxiv.org/abs/2606.04672), proposes a framework called `CTDG-SSM` that attacks both problems simultaneously -- and does it with a fraction of the parameters of competing methods.

## The two walls every CTDG model hits

Existing approaches still face two primary challenges: (1) long-range temporal dependencies (LRT) -- the ability to preserve and use node states and interactions over extended time horizons; and (2) long-range spatial dependencies (LRS) -- the ability to capture multi-hop structural interactions beyond immediate neighborhoods in dynamic graphs. These are not just academic concerns. These capabilities have made CTDGs increasingly important in domains including finance, healthcare, e-commerce, and social network analysis. In financial fraud detection, for instance, money laundering typically spans long transaction chains rather than isolated local interactions -- exactly the kind of pattern that existing models miss.

The field has split into two camps, each solving one problem while ignoring the other. Event-driven models like TGN and JODIE update node states at each interaction and are computationally lean, but they mainly capture short-term patterns and struggle to preserve long-range temporal context. Sequence-based models like DyGFormer and DyGMamba use Transformers or Mamba to explicitly target long-range temporal dependencies, but these methods pre-process temporal data by restricting attention to one-hop temporal neighborhoods, thereby significantly limiting their ability to maintain LRS. No existing model handles both at once.

## Building memory that knows the graph

The core insight of CTDG-SSM is to marry two powerful ideas: the HiPPO memory framework and graph Laplacian polynomials. **HiPPO** (High-order Polynomial Projection Operators) is a mathematical framework originally developed for sequence modeling. HiPPO defines a general mathematical and algorithmic framework for online compression and representation of sequential data via optimal projection onto polynomial bases, underpinning state-of-the-art models in recurrent neural networks, state-space systems, and Gaussian processes for efficient long-range sequence modeling. In plain terms: instead of trying to remember every past event, HiPPO compresses history into a compact set of polynomial coefficients that optimally summarize what happened.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models (arXiv)](https://arxiv.org/abs/2606.04672)
- [CTDG-SSM: Continuous-time Dynamic Graph State Space Models for Long Range Propagation (OpenReview / ICLR 2026)](https://openreview.net/forum?id=ihlRtPqPDL)
- [HiPPO: Recurrent Memory with Optimal Polynomial Projections (arXiv)](https://arxiv.org/abs/2008.07669)
- [DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models (arXiv)](https://arxiv.org/abs/2408.04713)
