Deep Structural Point Process for Learning Temporal Interaction Networks

Cao, Jiangxia; Lin, Xi-Jie; Cong, Xin; Guo, Shu; Tang, Hengzhu; Liu, Tingwen; Wang, Bin

doi:10.1007/978-3-030-86486-6_19

Cited by 10 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently neural network-based TPP has been proposed to model dynamic interaction. However, these works approximate higher-order interactions with pairwise interactions (Dai et al 2016;Trivedi et al 2019;Cao et al 2021). It has been shown in Hyper-SAGNN (Zhang, Zou, and Ma 2019) that directly modeling the higher-order interaction will result in better performance than decomposing them into pairwise interactions.…”

Section: Contributionsmentioning

confidence: 99%

“…Since nodes evolve as they interact, it is essential to employ dynamic node representations. In earlier works on dynamic networks (Trivedi et al 2019;Dai et al 2016;Cao et al 2021), node embeddings are updated based on the node embedding of the other node in the interaction. For example, consider edge event (v a , v b ) occurring at time t. To update node embeddings of v a , we use the node embeddings of v b and vice versa.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Representation Learning with Temporal Point Processes for Higher-Order Interaction Forecasting

Gracious

Dukkipati

2023

AAAI

View full text Add to dashboard Cite

The explosion of digital information and the growing involvement of people in social networks led to enormous research activity to develop methods that can extract meaningful information from interaction data. Commonly, interactions are represented by edges in a network or a graph, which implicitly assumes that the interactions are pairwise and static. However, real-world interactions deviate from these assumptions: (i) interactions can be multi-way, involving more than two nodes or individuals (e.g., family relationships, protein interactions), and (ii) interactions can change over a period of time (e.g., change of opinions and friendship status). While pairwise interactions have been studied in a dynamic network setting and multi-way interactions have been studied using hypergraphs in static networks, there exists no method, at present, that can predict multi-way interactions or hyperedges in dynamic settings. Existing related methods cannot answer temporal queries like what type of interaction will occur next and when it will occur. This paper proposes a temporal point process model for hyperedge prediction to address these problems. Our proposed model uses dynamic representation learning techniques for nodes in a neural point process framework to forecast hyperedges. We present several experimental results and set benchmark results. As far as our knowledge, this is the first work that uses the temporal point process to forecast hyperedges in dynamic networks.

show abstract

Section: Contributionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Dynamic Representation Learning with Temporal Point Processes for Higher-Order Interaction Forecasting

Gracious

Dukkipati

2023

AAAI

View full text Add to dashboard Cite

show abstract

“…To generate user/item representations, this section proposes the variational bipartite graph encoder (VBGE). Different from general homogeneous graphs [18], the user-item interactions can be regarded as a heterogeneous bipartite graph [19,20], where any two user nodes are connected with the evennumber-hop (e.g., 2-hop, 4-hop, etc). Nevertheless, traditional graph encoders [21,22,23] mostly aggregate node information from its direct (1-hop) neighbors, which does not explicitly aggregate user/item node from its homogeneous neighbors.…”

Section: B Variational Bipartite Graph Encodermentioning

confidence: 99%

Cross-Domain Recommendation to Cold-Start Users via Variational Information Bottleneck

Cao¹,

Sheng²,

Xu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Recommender systems have been widely deployed in many real-world applications, but usually suffer from the longstanding user cold-start problem. As a promising way, Cross-Domain Recommendation (CDR) has attracted a surge of interest, which aims to transfer the user preferences observed in the source domain to make recommendations in the target domain. Previous CDR approaches mostly achieve the goal by following the Embedding and Mapping (EMCDR) idea which attempts to learn a mapping function to transfer the pre-trained user representations (embeddings) from the source domain into the target domain. However, they pre-train the user/item representations independently for each domain, ignoring to consider both domain interactions simultaneously. Therefore, the biased pre-trained representations inevitably involve the domain-specific information which may lead to negative impact to transfer information across domains. In this work, we consider a key point of the CDR task: what information needs to be shared across domains? To achieve the above idea, this paper utilizes the information bottleneck (IB) principle, and proposes a novel approach termed as CDRIB to enforce the representations encoding the domainshared information. To derive the unbiased representations, we devise two IB regularizers to model the cross-domain/in-domain user-item interactions simultaneously and thereby CDRIB could consider both domain interactions jointly for de-biasing. With an additional contrastive information regularizer, CDRIB can also capture cross-domain user-user correlations. In this way, those regularizers encourage the representations to encode the domain-shared information, which has the capability to make recommendations in both domains directly. To the best of our knowledge, this paper is the first work to capture the domain-shared information for cold-start users via variational information bottleneck. Empirical experiments illustrate that CDRIB outperforms the state-of-the-art approaches on four realworld cross-domain datasets, demonstrating the effectiveness of adopting the information bottleneck for CDR.

show abstract

“…MMDNE [21], HTNE [49] and DSPP [4] employ the attention mechanism to avoid the inefficiency of the recurrent structure in training with large CTDGs. However, these works are restrictively dedicated to link prediction or timestamp prediction task.…”

Section: Temporal Point Process On Dynamic Graphmentioning

confidence: 99%

CEP3: Community Event Prediction with Neural Point Process on Graph

Wang¹,

Chen²,

He³

et al. 2022

Preprint

View full text Add to dashboard Cite

Many real world applications can be formulated as event forecasting on Continuous Time Dynamic Graphs (CTDGs) where the occurrence of a timed event between two entities is represented as an edge along with its occurrence timestamp in the graphs.However, most previous works approach the problem in compromised settings, either formulating it as a link prediction task on the graph given the event time or a time prediction problem given which event will happen next. In this paper, we propose a novel model combining Graph Neural Networks and Marked Temporal Point Process (MTPP) that jointly forecasts multiple link events and their timestamps on communities over a CTDG. Moreover, to scale our model to large graphs, we factorize the jointly event prediction problem into three easier conditional probability modeling problems.To evaluate the effectiveness of our model and the rationale behind such a decomposition, we establish a set of benchmarks and evaluation metrics for this event forecasting task. Our experiments demonstrate the superior performance of our model in terms of both model accuracy and training efficiency.

show abstract

Deep Structural Point Process for Learning Temporal Interaction Networks

Cited by 10 publications

References 21 publications

Dynamic Representation Learning with Temporal Point Processes for Higher-Order Interaction Forecasting

Dynamic Representation Learning with Temporal Point Processes for Higher-Order Interaction Forecasting

Cross-Domain Recommendation to Cold-Start Users via Variational Information Bottleneck

CEP3: Community Event Prediction with Neural Point Process on Graph

Contact Info

Product

Resources

About