Learning from Heterogeneous Student Behaviors for Multiple Prediction Tasks

Liu, Haobing; Zhu, Yanmin; Xu, Yanan

doi:10.1007/978-3-030-59416-9_18

Cited by 7 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tanjim et al [13] used a Transformer layer to learn item similarities from the interacted item sequence and used a convolution layer to obtain the user's intent from her actions on a particular category. Liu et al [52] modeled each kind of behavior sequence with an attention-based LSTM and modeled the implicit interactions among multiple behavior prediction tasks. Liu et al [53] further proposed a model to model interactions among multiple behavior prediction tasks explicitly.…”

Section: Sequential Behavior Prediction Based On Heterogeneous Behaviorsmentioning

confidence: 99%

See 1 more Smart Citation

Incorporating Heterogeneous User Behaviors and Social Influences for Predictive Analysis

Liu,

Zhu,

Wang

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Behavior prediction based on historical behavioral data have practical real-world significance. It has been applied in recommendation, predicting academic performance, etc. With the refinement of user data description, the development of new functions, and the fusion of multiple data sources, heterogeneous behavioral data which contain multiple types of behaviors become more and more common. In this paper, we aim to incorporate heterogeneous user behaviors and social influences for behavior predictions. To this end, this paper proposes a variant of Long-Short Term Memory (LSTM) which can consider context information while modeling a behavior sequence, a projection mechanism which can model multi-faceted relationships among different types of behaviors, and a multi-faceted attention mechanism which can dynamically find out informative periods from different facets. Many kinds of behavioral data belong to spatio-temporal data. An unsupervised way to construct a social behavior graph based on spatio-temporal data and to model social influences is proposed. Moreover, a residual learning-based decoder is designed to automatically construct multiple high-order cross features based on social behavior representation and other types of behavior representations. Qualitative and quantitative experiments on real-world datasets have demonstrated the effectiveness of this model.

show abstract

Section: Sequential Behavior Prediction Based On Heterogeneous Behaviorsmentioning

confidence: 99%

“…• APAMT [52]: APAMT models each kind of behavior sequence with an attention-based LSTM and models the implicit interactions among multiple tasks. We adopt it to handle PAP and PNBB tasks simultaneously.…”

Section: Baselinesmentioning

confidence: 99%

Incorporating Heterogeneous User Behaviors and Social Influences for Predictive Analysis

Liu,

Zhu,

Wang

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…• APAMT [21]: Attentional Profile-Aware Multi-Task model (APAMT) is proposed in our preliminary work. It leverages the Profile-aware LSTM and the soft-attention mechanism to model the daily behavior sequence.…”

Section: Comparison Baselinesmentioning

confidence: 99%

“…To address the first two challenges, we propose an attentional profile-aware multi-task model (APAMT) for modeling heterogeneous daily behaviors in our preliminary work [21]. More specifically, for heterogeneous daily behaviors, each kind of behavior sequence is modeled by a variant of LSTM named Profile-aware LSTM.…”

Section: Introductionmentioning

confidence: 99%

Jointly Modeling Heterogeneous Student Behaviors and Interactions Among Multiple Prediction Tasks

Liu,

Zhu,

Zang

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Prediction tasks about students have practical significance for both student and college. Making multiple predictions about students is an important part of a smart campus. For instance, predicting whether a student will fail to graduate can alert the student affairs office to take predictive measures to help the student improve his/her academic performance. With the development of information technology in colleges, we can collect digital footprints which encode heterogeneous behaviors continuously. In this paper, we focus on modeling heterogeneous behaviors and making multiple predictions together, since some prediction tasks are related and learning the model for a specific task may have the data sparsity problem. To this end, we propose a variant of LSTM and a soft-attention mechanism. The proposed LSTM is able to learn the student profileaware representation from heterogeneous behavior sequences. The proposed soft-attention mechanism can dynamically learn different importance degrees of different days for every student. In this way, heterogeneous behaviors can be well modeled. In order to model interactions among multiple prediction tasks, we propose a co-attention mechanism based unit. With the help of the stacked units, we can explicitly control the knowledge transfer among multiple tasks. We design three motivating behavior prediction tasks based on a real-world dataset collected from a college. Qualitative and quantitative experiments on the three prediction tasks have demonstrated the effectiveness of our model.

show abstract

Modeling Dynamic Social Behaviors with Time-Evolving Graphs for User Behavior Predictions

Zang

Zhu

Gong

et al. 2021

Database Systems for Advanced Applications

View full text Add to dashboard Cite

Learning from Heterogeneous Student Behaviors for Multiple Prediction Tasks

Cited by 7 publications

References 24 publications

Incorporating Heterogeneous User Behaviors and Social Influences for Predictive Analysis

Incorporating Heterogeneous User Behaviors and Social Influences for Predictive Analysis

Jointly Modeling Heterogeneous Student Behaviors and Interactions Among Multiple Prediction Tasks

Modeling Dynamic Social Behaviors with Time-Evolving Graphs for User Behavior Predictions

Contact Info

Product

Resources

About