Arrow Research search

Author name cluster

Achla Marathe

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers
1 author row

Possible papers

7

AAMAS Conference 2026 Conference Paper

Network-based Active Learning for Identifying Illicit Actors in Financial Transaction Networks

  • Amro Alabsi Aljundi
  • Abhijin Adiga
  • Christopher Barrett
  • Margaret J. Foster
  • Brian D. Klahn
  • Dustin Machi
  • Achla Marathe
  • Philip B. K. Potter

Identifying illicit transactions within financial networks is an important area of research. Available datasets are highly imbalanced, makingthedesignofmachinelearningmethodschallenging. Active learning, which carefully chooses data points for annotation, has been shown to improve performance for such problems. Here, we design a new approach, C2AL, for detecting illicit nodes in financial networks, which incorporates network correlations more explicitly. Our approach builds on prior work on active learning on networks, specifically, collective classification (CC), which uses predicted labels of neighboring nodes to improve classification. We extend this approach by incorporating the information from both underlying models of collective classification, as well as their contrastive information, into the active learning sample selection procedure. We show that C2AL significantly improves sample efficiency, requiring up to 48% fewer labeled samples than prior methods to achieve comparable detection performance across six financial network datasets. This work is licensed under a Creative Commons Attribution International 4. 0 License. Proc. of the 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026), C. Amato, L. Dennis, V. Mascardi, J. Thangarajah (eds.), May 25 – 29, 2026, Paphos, Cyprus. © 2026 International Foundation for Autonomous Agents and Multiagent Systems (www. ifaamas. org). https: //doi. org/10. 65109/GOCK1684

AAAI Conference 2021 Conference Paper

Persistence of Anti-vaccine Sentiment in Social Networks Through Strategic Interactions

  • A S M Ahsan-Ul Haque
  • Mugdha Thakur
  • Matthew Bielskas
  • Achla Marathe
  • Anil Vullikanti

Vaccination is the primary intervention for controlling the spread of infectious diseases. A certain level of vaccination rate (referred to as “herd immunity”) is needed for this intervention to be effective. However, there are concerns that herd immunity might not be achieved due to an increasing level of hesitancy and opposition to vaccines. One of the primary reasons for this is the cost of non-conformance with one’s peers. We use the framework of network coordination games to study the persistence of anti-vaccine sentiment in a population. We extend it to incorporate the opposing forces of the pressure of conforming to peers, herd-immunity and vaccination benefits. We study the structure of the equilibria in such games, and the characteristics of unvaccinated nodes. We also study Stackelberg strategies to reduce the number of nodes with anti-vaccine sentiment. Finally, we evaluate our results on different kinds of real world social networks.

AAMAS Conference 2018 Conference Paper

Behavior Model Calibration for Epidemic Simulations

  • Meghendra Singh
  • Achla Marathe
  • Madhav V. Marathe
  • Samarth Swarup

Computational epidemiologists frequently employ large-scale agentbased simulations of human populations to study disease outbreaks and assess intervention strategies. The agents used in such simulations rarely capture the real-world decision-making of human beings. An absence of realistic agent behavior can undermine the reliability of insights generated by such simulations and might make them ill-suited for informing public health policies. In this paper, we address this problem by developing a methodology to create and calibrate an agent decision making model for a large multiagent simulation, using survey data. Our method optimizes a cost vector associated with the various behaviors to match the behavior distributions observed in a detailed survey of human behaviors during influenza outbreaks. Our approach is a data-driven way of incorporating decision making for agents in large-scale epidemic simulations.

AAMAS Conference 2018 Conference Paper

Designing Incentives to Maximize the Adoption of Rooftop Solar Technology

  • Aparna Gupta
  • Samarth Swarup
  • Achla Marathe
  • Anil Vullikanti
  • Kiran Lakkaraju
  • Joshua Letchford

Household level rooftop solar technology adoption is rising in many regions, driven by a multitude of factors, including falling prices and incentives such as tax breaks. It has also been shown in recent research that peer effects have an important role in the spread of solar adoption. This leads to a natural problem of how to design incentives to maximize adoption in such a model. While this is an instance of an “influence maximization” problem, prior results from the influence maximization literature cannot be used directly. In this work, we extend prior results from the literature on the use of submodularity to obtain a greedy approximation. We use this new result to do optimal “seed set” selection for a highly detailed, datadriven, agent-based model of household rooftop solar adoption.

AAMAS Conference 2017 Conference Paper

A Comparison of Targeted Layered Containment Strategies for a Flu Pandemic in Three US Cities

  • Shuyu Chu
  • Samarth Swarup
  • Jiangzhuo Chen
  • Achla Marathe

We study strategies for targeted layered containment of an influenza pandemic in three US cities: Miami, Seattle, and Chicago. Differences in demographic, geographic, and other structures lead to differences in the social interaction networks in the three cities. This has consequences for how the containment strategies should be applied to mitigate the spread. We use large-scale simulations to study these containment strategies and show differences in outcomes across the three cities.

IS Journal 2015 Journal Article

Model-Based Forecasting of Significant Societal Events

  • Naren Ramakrishnan
  • Chang-Tien Lu
  • Madhav Marathe
  • Achla Marathe
  • Anil Vullikanti
  • Stephen Eubank
  • Scotland Leman
  • Michael Roan

The article outlines some salient aspects of Embers-generated forecasts through its design considerations, system architecture, and user interface.

TIST Journal 2013 Journal Article

Analysis of friendship network and its role in explaining obesity

  • Achla Marathe
  • Zhengzheng Pan
  • Andrea Apolloni

We employ Add Health data to show that friendship networks, constructed from mutual friendship nominations, are important in building weight perception, setting weight goals, and measuring social marginalization among adolescents and young adults. We study the relationship between individuals' perceived weight status, actual weight status, weight status relative to friends' weight status, and weight goals. This analysis helps us understand how individual weight perceptions might be formed, what these perceptions do to the weight goals, and how friends' relative weight affects weight perception and weight goals. Combining this information with individuals' friendship network helps determine the influence of social relationships on weight-related variables. Multinomial logistic regression results indicate that relative status is indeed a significant predictor of perceived status, and perceived status is a significant predictor of weight goals. We also address the issue of causality between actual weight status and social marginalization (as measured by the number of friends) and show that obesity precedes social marginalization in time rather than the other way around. This lends credence to the hypothesis that obesity leads to social marginalization not vice versa. Attributes of the friendship network can provide new insights into effective interventions for combating obesity since adolescent friendships provide an important social context for weight-related behaviors.

v2026.09.13