Human-AI Collaboration with Bandit Feedback

Human-machine complementarity is important when neither the algorithm nor the human yield dominant performance across all instances in a given domain. Most research on algorithmic decision-making solely centers on the algorithm's performance, while recent work that explores human-machine collaboration has framed the decision-making problems as classification tasks. In this paper, we first propose and then develop a solution for a novel human-machine collaboration problem in a bandit feedback setting. Our solution aims to exploit the human-machine complementarity to maximize decision rewards. We then extend our approach to settings with multiple human decision makers. We demonstrate the effectiveness of our proposed methods using both synthetic and real human responses, and find that our methods outperform both the algorithm and the human when they each make decisions on their own. We also show how personalized routing in the presence of multiple human decision-makers can further improve the human-machine team performance.

A NEW MODEL FOR FUZZY PERSONALIZED ROUTE PLANNING USING FUZZY LINGUISTIC PREFERENCE RELATION

This paper proposes a new model for personalized route planning under uncertain condition. Personalized routing, involves different sources of uncertainty. These uncertainties can be raised from user’s ambiguity about their preferences, imprecise criteria values and modelling process. The proposed model uses Fuzzy Linguistic Preference Relation Analytical Hierarchical Process (FLPRAHP) to analyse user’s preferences under uncertainty. Routing is a multi-criteria task especially in transportation networks, where the users wish to optimize their routes based on different criteria. However, due to the lake of knowledge about the preferences of different users and uncertainties available in the criteria values, we propose a new personalized fuzzy routing method based on the fuzzy ranking using center of gravity. The model employed FLPRAHP method to aggregate uncertain criteria values regarding uncertain user’s preferences while improve consistency with least possible comparisons. An illustrative example presents the effectiveness and capability of the proposed model to calculate best personalize route under fuzziness and uncertainty.

ALL-TO-ALL BROADCASTING ALGORITHMS ON HONEYCOMB NETWORKS AND APPLICATIONS

This paper presents two simple all-to-all broadcasting algorithms on honeycomb mesh. Consider a network with n processors, one has personalized routing strategy at each node and it requires a 3n communication time complexity. This communication time can be reduced to n because the computation time is always assumed to be much lower than the communication time. The other is based on a Hamiltonian path and has a 2n communication time complexity. We show how they can be used to get parallel solutions to a class of problems on honeycomb networks, among others Prefix Sums, Maximal Vectors, Maximal Sum Subsegment, Parenthesis Matching, Decoding Binary Tree, and Sorting. In our knowledge, these all-to-all broadcast algorithms are the only ones so far exhibited on a honeycomb.