Interpretable Transformer Hawkes Processes: Unveiling Complex Interactions in Social Networks
Zizhuo Meng, Ke Wan, Yadong Huang, Zhidong Li, Yang Wang, Feng Zhou
TL;DR
This work tackles the interpretability and expressiveness gap in deep point processes for social networks by introducing interpretable Transformer Hawkes Processes (ITHP). ITHP modifies Transformer Hawkes Process to explicitly capture interactions between event types and to model non-event intervals via a fully attention based intensity, aligning with nonlinear Hawkes kernels. The approach uses concatenated embeddings, a simplified attention mechanism, and a time varying trigger kernel to provide interpretable intra-type influences and flexible intensity dynamics, with training via maximum likelihood. Empirical results on synthetic and public datasets show that ITHP achieves competitive predictive performance while offering rich interpretability through learned interaction kernels and attention maps, enabling insights into user or group influences in social networks.
Abstract
Social networks represent complex ecosystems where the interactions between users or groups play a pivotal role in information dissemination, opinion formation, and social interactions. Effectively harnessing event sequence data within social networks to unearth interactions among users or groups has persistently posed a challenging frontier within the realm of point processes. Current deep point process models face inherent limitations within the context of social networks, constraining both their interpretability and expressive power. These models encounter challenges in capturing interactions among users or groups and often rely on parameterized extrapolation methods when modelling intensity over non-event intervals, limiting their capacity to capture intricate intensity patterns, particularly beyond observed events. To address these challenges, this study proposes modifications to Transformer Hawkes processes (THP), leading to the development of interpretable Transformer Hawkes processes (ITHP). ITHP inherits the strengths of THP while aligning with statistical nonlinear Hawkes processes, thereby enhancing its interpretability and providing valuable insights into interactions between users or groups. Additionally, ITHP enhances the flexibility of the intensity function over non-event intervals, making it better suited to capture complex event propagation patterns in social networks. Experimental results, both on synthetic and real data, demonstrate the effectiveness of ITHP in overcoming the identified limitations. Moreover, they highlight ITHP's applicability in the context of exploring the complex impact of users or groups within social networks.