New Zealand

Maria Luisa Sein-Echaluce, Dolores Leris, Joaquin Castello, Vicente Martinez, Jose Manuel Correas and Natalia Boal (October 1st 2009). Cooperation between Universities to Develop an Online Learning Environment in Mathematics, Technology, Education and Development, Aleksandar Lazinica and Carlos Calafate, IntechOpen, DOI: 10.5772/7284.

Punnarumol Temdee (April 22nd 2020). Smart Learning Environment: Paradigm Shift for Online Learning, Multi Agent Systems - Strategies and Applications, Ricardo López - Ruiz, IntechOpen, DOI: 10.5772/intechopen.85787. 

Alberto Cano (February 19th 2020). Introductory Chapter: Data Streams and Online Learning in Social Media, Social Media and Machine Learning, Alberto Cano, IntechOpen, DOI: 10.5772/intechopen.90826.

This talk is about how to design differentially private algorithm in contextual dynamic pricing setting. 


AAMAS 2020

Differentially Private Contextual Dynamic Pricing

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible. The experience for on-site participants would closely approximate a normal pre-COVID *ACL conference, with 5-6 thematically organized parallel sessions and live Q/A and interactive discussion immediately after the talks. Presentations by virtual participants will be equitably interleaved with those of on-site participants, projected on the auditorium screens as if on-site, and also followed immediately by live Q/A and interactive discussion at a time during reasonable waking hours for the virtual presenter. For all participants, on-site and virtual, who are unable to attend a session due to either time-zone issues or because they are participating in another session live, talk recordings and slides will be available online at a minimum after the live presentation (and in many cases before as well), and questions may be submitted in advance on session-specific discussion boards and answered live in session with the usual visual aids if desired.

<iframe style="width:700px;height:400px" src="https://online.fliphtml5.com/ebtyf/ceby/"  seamless="seamless" scrolling="no" frameborder="0" allowtransparency="true" allowfullscreen="true" ></iframe>

Please Note: The EMNLP registration system is not currently connected to the underline site as we are still in the process of building out EMNLP 2021. You will receive access instructions from underline the week of November 1st. 

Access is given only to EMNLP upon registration, if you have not registered please do so [here](https://2021.emnlp.org/registration).

Registered attendees will receive access the week of November 1st.

EMNLP 2021

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible.

technical paper

AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). The aim of the joint conference is to provide a single, high-profile, internationally-respected archival forum for scientific research in the theory and practice of autonomous agents and multi-agent systems.

Browse keynotes, discussions, panels and over 300 presentations.


AAMAS is the leading scientific conference for research in autonomous agents and multi-agent systems. The AAMAS conference series was initiated in 2002 as the merging of three respected scientific meetings: the International Conference on Multi-Agent Systems (ICMAS), the International Workshop on Agent Theories, Architectures, and Languages (ATAL), and the International Conference on Autonomous Agents (AA). 

In many practical scenarios, a population is divided into disjoint groups for better administration, such as electorates into political districts and students into school districts. However, grouping people arbitrarily may lead to biased partitions, raising concerns of gerrymandering in political districting and racial segregation in schools. To counter such issues, in this paper, we conceptualize such problems in a voting scenario, and given an initial grouping, we propose the Fair Regrouping problem to redistribute a given set of people into k groups, where each person has a preferred alternative and a set of groups they can be moved to, such that the maximum margin of victory of any group is minimized. We also propose the Fair Connected Regrouping problem which additionally requires the people within each group to be connected. We show that the Fair Regrouping problem is NP-complete for plurality voting even if we have only 3 alternatives, but admits polynomial time algorithms if everyone can be moved to any group. We further show that the Fair Connected Regrouping problem is NP-complete for plurality voting even if we have only 2 alternatives and k = 2. Finally, we propose heuristic algorithms for both problems and show their effectiveness in political districting in the U.K. and in lowering racial segregation in public schools in the U.S.


Minimizing Margin of Victory for  Fair Political and Educational Districting

Controlling recurrent infectious diseases is a vital yet complicated problem. A large portion of the controlling epidemic relies on patients visit clinics voluntarily. However, they may already transmit the disease to their contacts by the time they feel sick enough to visit the clinic, especially for conditions with a long incubation period. Therefore, active screening/case finding was deployed to provide a powerful yet expensive means to control disease spread in recent years. To make active screening success a given limit budget, one of the challenges that need to be addressed is that we do not know the exact state of each patient. Given the number of horizon and budget we have in each time step, we also need to plan our screening efficiently and screening the vital patients in time. Thus, we apply a reinforcement learning approach to solve active screening problems on the network SIS disease model. The first contribution of this work is that we identify three significant challenges in active screening problems: partially observable states, combinatorial action choice, high-dimensional state-action space. We further propose the corresponding solutions to overcome these challenges. Specifically, we resolve the issue of high-dimensional state-action space by encoding the actions and partially observable states into a lower dimension form, which is done by either manually, using domain expertise, or automatically, using the state of the art GCN approach. We show that our approach can scale up to large graphs and perform decently compared to other baselines of previous literature and current practice.

Who and When to Screen: Multi-Round Active Screening for Recurrent Infectious Diseases Under Uncertainty

How should one combine noisy information from diverse sources to make an inference about an objective ground truth? This frequently recurring, normative question lies at the core of statistics, machine learning, policy-making, and everyday life. It has been called "combining forecasts", "meta-analysis", "ensembling", and the "MLE approach to voting", among other names. Past studies typically assume that noisy votes are identically and independently distributed (i.i.d.), but this assumption is often unrealistic. Instead, we assume that votes are independent but not necessarily identically distributed and that our ensembling algorithm has access to certain auxiliary information related to the underlying model governing the noise in each vote. In our present work, we: (1) define our problem and argue that it reflects common and socially relevant real world scenarios, (2) propose a multi-arm bandit noise model and count-based auxiliary information set, (3) derive maximum likelihood aggregation rules for ranked and cardinal votes under our noise model, (4) propose, alternatively, to learn an aggregation rule using an order-invariant neural network, and (5) empirically compare our rules to common voting rules and naive experience-weighted modifications. We find that our rules successfully use auxiliary information to outperform the naive baselines.


Objective Social Choice

A serious challenge when finding influential actors in real-world social networks, to enable efficient community-wide interventions, is the lack of knowledge about the structure of the underlying network. Current state-of-the-art methods rely on hand-crafted sampling algorithms; these methods sample nodes and their neighbours in a carefully constructed order and choose opinion leaders from this discovered network to maximize influence spread in the(unknown) complete network.
In this work, we propose a reinforcement learning framework to discover effective network sampling heuristics by leveraging automatically learnt node and graph representations that encode important structural properties of the network. At training time, the method identifies portions of the network such that the nodes selected from this sampled subgraph can effectively influence nodes in the complete network. The output of this training is a transferable, adaptive policy that identifies an effective sequence of nodes to query on unseen graphs. The success of this policy is underpinned by a set of careful choices for embedding local and global information about the graph and providing appropriate reward signals during training. We experiment with real-world social networks from four different domains and show that the policies learned by our RL agent provide a 7-23% improvement over the current state-of-the-art method


Influence maximization in unknown social networks: Learning Policies for Effective Graph Sampling : Policies for Effective Graph Sampling

Function approximation is a powerful approach for structuring large decision problems that has facilitated great achievements in the areas of reinforcement learning and game playing. Regression counterfactual regret minimization (RCFR) is a simple algorithm for approximately solving imperfect information games with normalized rectified linear unit (ReLU) parameterized policies. In contrast, the more conventional softmax parameterization is standard in the field of reinforcement learning and yields a regret bound with a better dependence on the number of actions. We derive approximation error-aware regret bounds for $(\Phi, f)$-regret matching, which applies to a general class of link functions and regret objectives. These bounds recover a tighter bound for RCFR and provide a theoretical justification for RCFR implementations with alternative policy parameterizations ($f$-RCFR), including softmax. We provide exploitability bounds for $f$-RCFR with the polynomial and exponential link functions in zero-sum imperfect information games and examine empirically how the link function interacts with the severity of the approximation. We find that the previously studied ReLU parameterization performs better when the approximation error is small while the softmax parameterization can perform better when the approximation error is large.


Alternative Function Approximation Parameterizations for Solving Games: An Analysis of f-Regression Counterfactual Regret Minimization

Improved Algorithms for Learning Equilibria in Simulation-Based Games

In the field of informed decision-making, the usage of a single diagnostic expert system has limitations when dealing with complicated circumstances. The usage of a multi-agent information fusion (MAIF) system can mitigate this situation, as it allows multiple agents collaborating to solve the problems in a complex environ- ment. However, the MAIF system needs to handle the uncertainty problem between different agents objectively at the same time. Target to this goal, this study reconstructs the generation of basic probability assignments (BPAs) based on the framework of evidence theory, and presents the uncertainty relationship between recognition sets, which are beneficial to the applications of the MAIF system. On the basis of evidence distance measurement, our method demonstrates the effectiveness and extendibility in numerical examples, and improves the accuracy and anti-interference ability during the identification process in the MAIF system.


Uncertainty Modeling in Multi-agent Information Systems

In many multiagent domains, and particularly in tightly coupled domains, teasing an agent's contribution to the system performance based on a single episodic return is difficult. This well-known difficulty hits state-to-action mapping approaches such as neural networks trained by evolutionary algorithms particularly hard. This paper introduces fitness critics, which leverage the expected fitness to evaluate an agent's performance. This approach turns a sparse performance metric (policy evaluation) into a dense performance metric (state-action evaluation) by relating the episodic feedback to the state-action pairs experienced during the execution of that policy. In the tightly-coupled multi-rover domain (where multiple rovers have to perform a particular task simultaneously), only teams using fitness critics were able to demonstrate effective learning on tasks with tight coupling while other coevolved teams were unable to learn at all.


Multi-level Fitness Critics for Coevolution

We consider exploration tasks in which an autonomous mobile robot incrementally builds maps of initially unknown indoor environments. In such tasks, the robot makes a sequence of decisions on where to move next that, usually, are based on knowledge about the observed parts of the environment. 
In this paper, we present an approach that exploits a prediction of the geometric structure of the unknown parts of an environment to improve exploration performance. In particular, we leverage an existing method that reconstructs the layout of an environment starting from a partial grid map and that predicts the shape of partially observed rooms on the basis of geometric features representing the regularities of the indoor environment. Then, we originally employ the predicted layout to estimate the amount of new area the robot would observe from candidate locations in order to inform the selection of the next best location and to early stop the exploration when no further relevant area is expected to be discovered. Experimental activities show that our approach is able to effectively predict the layout of partially observed rooms and to use such knowledge to speed up the exploration.

Downloads

Next from AAMAS 2020

Minimizing Margin of Victory for Fair Political and Educational Districting

Similar lecture

Learning and Evaluating a Differentially Private Pre-trained Language Model

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads