Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· 0 citations· 42 references
TL;DR
CARD, a context-aware routing framework that replaces static fusion with step-wise evidence arbitration, is proposed, a context-aware routing framework that achieves state-of-the-art accuracy and stronger robustness.
Abstract
Information diffusion prediction forecasts future participants from an observed cascade prefix, enabling proactive intervention in applications such as viral marketing and misinformation mitigation. Most existing models leverage two data sources: the global social graph (exposure/trust pathways) and cascade-induced interaction relations (interest-driven co-adoption), following a ''learn-then-fuse'' pipeline that encodes both graphs with GNNs and combines them via gated fusion to condition a sequential decoder. However, we find the two views are systematically mismatched: interaction edges are largely disjoint from social links, most social neighbors never co-activate within the same cascade, and the resulting embeddings lie on near-orthogonal manifolds with negligible correspondence. With such mismatch, static fusion is ill-posed: when the views disagree, fusion enforces a compromise and can cause negative interference. We further identify three reliability mechanisms that determine when each view should be trusted: (1) behavioral consensus across views is a high-fidelity signal of influence; (2) social cues are essential in cold-start regimes where interactions are sparse and biased; and (3) social ties dominate early seeding, while interaction patterns govern the late viral stage. Motivated by these, we propose CARD, a context-aware routing framework that replaces static fusion with step-wise evidence arbitration. CARD constructs an expert pool with social and interaction experts, a consensus expert that activates when both views are confirmed to behavioral consensus, and a graph-agnostic prior expert for noisy fallback. A router hard-selects the single most reliable expert at each step, so the decoder receives a targeted signal rather than a blurred mixture. Extensive experiments on four real-world datasets show that CARD achieves state-of-the-art accuracy and stronger robustness.
A proof-of-concept, mechanism-grounded framework that treats trust as a bounded, directed, and diffusible state on a temporal heterogeneous graph and couples that state to learned influence pathways and budget-constrained intervention optimization and demonstrates internal feasibility rather than established real-world...
A hybrid model is built that combines the two models' influence-spread estimates through a tunable weighting parameter, and a greedy seed-selection procedure optimizes over the combined signal rather than either model alone, suggesting that treating diffusion as a blend of probabilistic and threshold-based behavior is...
Aditya Raj, D. Malleswari· Adolescência e Saúde· 0 citations
The reliability and security of recommendation systems are now very important issues in the current digital era. ecosystems. Traditional collaborative filtering and hybrid methods fail to consider user. They are subject to data sparsity, shilling attacks, and behavioral noise, due to their trustworthiness. This study p...
Kumar D. Durai, Annabel L. Sherly Puspha· International journal on art...· 0 citations
A network-based framework that estimates influence directly from retweet networks using the independent cascade model and a polynomial-time dynamic programming algorithm that computes the optimal placement of coordinated nodes, providing an upper bound on their achievable influence are introduced.
N. Di Marco, Matteo Cinelli, Shin-Ichi Nakano et al.· arXiv.org· 0 citations
AdaptedKG is presented, which derives calibrated KG evidence for each training example without adding graph representations to the recommendation model and compares the observed context with structurally matched alternatives to identify relational paths that are unusually prominent and uses them to build a local KG vie...
Zichun Jin, Zihan Zhou, Yi-Nan Liu et al.· arXiv.org· 0 citations
Misinformation spreads rapidly through online social networks, causing measurable harm to public health and undermining democratic discourse. The Influence Minimization problem, selecting nodes to immunise in order to contain such spread, is the structural inverse of the widely studied Influence Maximization proble...
A. Al Tawil, Amnah Alshahrani, A. Shaban et al.· Scientific Reports· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.