More Like this

1. Causal Learning with Delays Up to 21 Hours.

   Zhang, Yiwen; Rottman, Benjamin (January 2021, Proceedings of the Annual Conference of the Cognitive Science Society)

   Fitch, T; Lamm, C; Leder, H; Tessmar, K (Ed.)

   Delays between causes and effects are commonly found in cause-effect relationships in real life. However, previous studies have only investigated delays on the order of seconds. In the current study we tested whether people can learn a cause- effect relation with hour long delays. The delays between the cause and effect were either 0, 3, 9, or 21 hours, and the study lasted 16 days. Surprisingly, we found that participants were able to learn the causal relation about equally as well in all four conditions. These findings demonstrate a remarkable ability to accurately learn causal relations in a realistic timeframe that has never been tested before. 

   more » « less
2. Causal Learning with Two Causes over Weeks

   Willett, Ciara L; Rottman, Benjamin M (January 2020, Proceedings of the Annual Conference of the Cognitive Science Society)

   Denison, S; Mack, M; Xu, Y; null (Ed.)

   When making causal inferences, prior research shows that people are capable of controlling for alternative causes. These studies, however, utilize artificial inter-trial intervals on the order of seconds; in real-life situations people often experience data over days and weeks (e.g., learning the effectiveness of two new medications over multiple weeks). In the current study, participants learned about two possible causes from data presented in a traditional trial-by-trial paradigm (rapid series of trials) versus a more naturalistic paradigm (one trial per day for multiple weeks via smartphone). Our results suggest that while people are capable of detecting simple cause-effect relations that do not require controlling for another cause when learning over weeks, they have difficulty learning cause-effect relations that require controlling for alternative causes. 

   more » « less
3. One-Class Order Embedding for Dependency Relation Prediction

   https://doi.org/10.1145/3331184.3331249  

   Chiang, Meng-Fen; Lim, Ee-Peng; Lee, Wang-Chien; Ashok, Xavier Jayaraj; Prasetyo, Philips Kokoh (July 2019, Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval)

   Learning the dependency relations among entities and the hierarchy formed by these relations by mapping entities into some order embedding space can effectively enable several important applications, including knowledge base completion and prerequisite relations prediction. Nevertheless, it is very challenging to learn a good order embedding due to the existence of partial ordering and missing relations in the observed data. Moreover, most application scenarios do not provide non-trivial negative dependency relation instances. We therefore propose a framework that performs dependency relation prediction by exploring both rich semantic and hierarchical structure information in the data. In particular, we propose several negative sampling strategies based on graph-specific centrality properties, which supplement the positive dependency relations with appropriate negative samples to effectively learn order embeddings. This research not only addresses the needs of automatically recovering missing dependency relations, but also unravels dependencies among entities using several real-world datasets, such as course dependency hierarchy involving course prerequisite relations, job hierarchy in organizations, and paper citation hierarchy. Extensive experiments are conducted on both synthetic and real-world datasets to demonstrate the prediction accuracy as well as to gain insights using the learned order embedding. 

   more » « less
4. How Augmented Reality Affects Collaborative Learning of Physics: a Qualitative Analysis

   Unahalekhaka, A.; Radu, I.; Schneider, B. (July 2019, Computer-supported collaborative learning)

   Augmented reality (AR) is a powerful visualization tool to support learning of scientific concepts across learners of various ages. AR can make information otherwise invisible visible in the physical world in real-time. In this study, we are looking at a subset of data from a larger study (N=120), in which participant pairs interacted with an augmented sound producing speaker. We explored the learning behaviors in eight pairs of learners (N=16) who participated in an unstructured physics activity under two conditions: with or without AR. Comparing behaviors between the two experimental conditions, we found that AR affected learning in four different ways: participants in the AR condition (1) learned more about visual concepts (ex: magnetic field structures) but learned less about nonvisual content (ex: relationship between electricity and physical movement); (2) stopped exploring the system faster than NonAR participants; (3) used less aids in exploration and teaching; and (4) spent less time in teaching their collaborators. We discuss implications of those results for designing collaborative learning activities with augmented reality. 

   more » « less
5. Heterogeneous Graph Structure Learning for Graph Neural Networks

   https://doi.org/10.1609/aaai.v35i5.16600  

   Zhao, Jianan; Wang, Xiao; Shi, Chuan; Hu, Binbin; Song, Guojie; Ye, Yanfang (May 2021, Proceedings of the AAAI Conference on Artificial Intelligence)

   Heterogeneous Graph Neural Networks (HGNNs) have drawn increasing attention in recent years and achieved outstanding performance in many tasks. The success of the existing HGNNs relies on one fundamental assumption, i.e., the original heterogeneous graph structure is reliable. However, this assumption is usually unrealistic, since the heterogeneous graph in reality is inevitably noisy or incomplete. Therefore, it is vital to learn the heterogeneous graph structure for HGNNs rather than rely only on the raw graph structure. In light of this, we make the first attempt towards learning an optimal heterogeneous graph structure for HGNNs and propose a novel framework HGSL, which jointly performs Heterogeneous Graph Structure Learning and GNN parameters learning for classification task. Different from traditional GSL on homogeneous graph, considering the heterogeneity of different relations in heterogeneous graph, HGSL generates each relation subgraph independently. Specifically, in each generated relation subgraph, HGSL not only considers the feature similarity by generating feature similarity graph, but also considers the complex heterogeneous interactions in features and semantics by generating feature propagation graph and semantic graph. Then, these graphs are fused to a learned heterogeneous graph and optimized together with a GNN towards classification objective. Extensive experiments on real-world graphs demonstrate that the proposed framework significantly outperforms the state-of-the-art methods. 

   more » « less