TY - GEN
T1 - Peer learning through targeted dynamic groups formation
AU - Wei, Dong
AU - Koutis, Ioannis
AU - Roy, Senjuti Basu
N1 - Funding Information:
VIII. CONCLUSION We initiate the study of peer-learning processes in rounds. The problem is motivated by practical considerations of groups in online social networks or offline classroom learning. In each round, the participants are split into groups and learn from interactions within their group. The objective is to find a sequence of groupings that will maximize the total knowledge at the end of the process. We introduce a model and an associated algorithmic framework DYGROUPS for this problem. Using the insights we gain from our theoretical study, we design experiments with human subjects that provide evidence corroborating our hypothesis that the choice of groupings can indeed significantly impact the total amount of learning. ACKNOWLEDGMENT Dong Wei and Senjuti Basu Roy are supported by the NSF, CAREER Award #1942913,IIS #2007935, IIS #1814595, and by the Office of Naval Research Grant No:N000141812838. I. Koutis is supported by the NSF, CCF Awards #2039863 and #1813374.
Publisher Copyright:
© 2021 IEEE.
PY - 2021/4
Y1 - 2021/4
N2 - Peer groups leverage the presence of knowledgeable individuals in order to increase the knowledge level of other participants. The 'smart' formation of peer groups can thus play a crucial role in educational settings, including online social networks and learning platforms. Indeed, the targeted groups formation problem, where the objective is to maximize a measure of aggregate knowledge, has received considerable attention in recent literature. In this paper we initiate a dynamic variant of the problem that, unlike previous works, allows the change of group composition over time while still targeting to maximize the aggregated knowledge level. The problem is studied in a principled way, using a realistic learning gain function and for two different interaction modes among the group members. On the algorithmic side, we present DyGroups, a generic algorithmic framework that is greedy in nature and highly scalable. We present non-trivial proofs to demonstrate theoretical guarantees for DyGroups in a special case. We also present real peer learning experiments with humans, and perform synthetic data experiments to demonstrate the effectiveness of our proposed solutions by comparing against multiple appropriately selected baseline algorithms.
AB - Peer groups leverage the presence of knowledgeable individuals in order to increase the knowledge level of other participants. The 'smart' formation of peer groups can thus play a crucial role in educational settings, including online social networks and learning platforms. Indeed, the targeted groups formation problem, where the objective is to maximize a measure of aggregate knowledge, has received considerable attention in recent literature. In this paper we initiate a dynamic variant of the problem that, unlike previous works, allows the change of group composition over time while still targeting to maximize the aggregated knowledge level. The problem is studied in a principled way, using a realistic learning gain function and for two different interaction modes among the group members. On the algorithmic side, we present DyGroups, a generic algorithmic framework that is greedy in nature and highly scalable. We present non-trivial proofs to demonstrate theoretical guarantees for DyGroups in a special case. We also present real peer learning experiments with humans, and perform synthetic data experiments to demonstrate the effectiveness of our proposed solutions by comparing against multiple appropriately selected baseline algorithms.
KW - Dynamic Graph Partition
KW - Groups Formation
KW - Peer Learning
UR - http://www.scopus.com/inward/record.url?scp=85112866687&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85112866687&partnerID=8YFLogxK
U2 - 10.1109/ICDE51399.2021.00018
DO - 10.1109/ICDE51399.2021.00018
M3 - Conference contribution
AN - SCOPUS:85112866687
T3 - Proceedings - International Conference on Data Engineering
SP - 121
EP - 132
BT - Proceedings - 2021 IEEE 37th International Conference on Data Engineering, ICDE 2021
PB - IEEE Computer Society
T2 - 37th IEEE International Conference on Data Engineering, ICDE 2021
Y2 - 19 April 2021 through 22 April 2021
ER -