Lune

SIGIR2026Top-tier venue

Inductive Dual-Polarity Modeling via Static-Dynamic Disentanglement for Dynamic Signed Networks

Yikang Hou, Junjie Huang, Yijun Ran, Tao Jia

Abstract

Dynamic signed networks (DSNs) are common in online platforms, where time-stamped positive and negative relations evolve over time. A core task in DSNs is dynamic edge prediction, which forecasts future relations by jointly modeling edge existence and polarity (positive, negative, or non-existent). However, existing dynamic signed network embedding (DSNE) methods often entangle positive and negative signals within a shared temporal state and rely on node-specific temporal trajectories, which can obscure polarity-asymmetric dynamics and harm inductive generalization, especially under cold-start evaluation. We study an inductive setting where each test edge contains at least one endpoint node held out from training, while its interactions prior to the prediction time are available as historical evidence. The model must therefore infer representations for unseen nodes solely from such limited history. We propose IDP-DSN, an Inductive Dual-Polarity framework for Dynamic Signed Networks. IDP-DSN maintains sign-selective memories to model positive and negative temporal dynamics separately, performs history-only neighborhood inference for unseen nodes (instead of learned node-wise trajectories), and enforces polarity-wise static--dynamic disentanglement via an orthogonality regularizer. Experiments on BitcoinAlpha, BitcoinOTC, Wiki-RfA, and Epinions demonstrate consistent improvements over the strongest baselines, achieving relative Macro-F1 gains of 16.8/23.4%, 16.9/24%, 30.1/25.5%, and 18.7/28.9% in the transductive/inductive settings, respectively. These results highlight the effectiveness of IDP-DSN on DSNs, particularly under inductive cold-start evaluation for dynamic signed edge prediction.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Provably expressive temporal graph networks cites Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks
  • Provably expressive temporal graph networks cites Inductive representation learning on temporal graphs
  • Signed Graph Neural Network with Latent Groups cites SDGNN: Learning Node Representation for Signed Directed Networks
  • Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks cites Inductive representation learning on temporal graphs
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on9

  1. Inductive representation learning on temporal graphsDa Xu, Chuanwei Ruan, Evren Körpeoglu, Sushant Kumar et al.ICLR 2020 · 901 citations
  2. Inductive Representation Learning in Temporal Networks via Causal Anonymous WalksYanbang Wang, Yen-Yu Chang, Yunyu Liu, Jure Leskovec et al.ICLR 2021 · 326 citations
  3. SDGNN: Learning Node Representation for Signed Directed NetworksJunjie Huang, Huawei Shen, Liang Hou, Xueqi ChengAAAI 2021 · 128 citations
  4. Provably expressive temporal graph networksAmauri H. Souza, Diego Mesquita, Samuel Kaski, Vikas GargNeurIPS 2022 · 89 citations
  5. Signed Graph Neural Network with Latent GroupsHaoxin Liu, Ziwei Zhang, Peng Cui, Yafeng Zhang et al.KDD 2021 · 38 citations

Related papers

  1. ASiNE: Adversarial Signed Network EmbeddingYeon-Chang Lee, Nayoun Seo, Kyungsik Han, Sang-Wook KimSIGIR 2020 · 33 citations
  2. RSGNN: A Model-agnostic Approach for Enhancing the Robustness of Signed Graph Neural NetworksZeyu Zhang, Jiamou Liu, Xianda Zheng, Yifei Wang et al.WWW 2023 · 32 citations
  3. Dynamic Representation Learning with Temporal Point Processes for Higher-Order Interaction ForecastingTony Gracious, Ambedkar DukkipatiAAAI 2023 · 7 citations
  4. SigFJProp: Lightweight and Scalable Signed Graph Learning via Opinion DynamicsYubo Sun, Haoxin Sun, Zhongzhi ZhangKDD 2026
  5. Bi-Dynamic Graph ODE for Opinion EvolutionBowen Duan, Henggang Deng, Jinghua Piao, Huandong Wang et al.KDD 2025
Dusk over the sea between two cliffs drawn in fine vertical lines