Search Results for author: Long Tran-Thanh

Found 32 papers, 5 papers with code

Invariant Lipschitz Bandits: A Side Observation Approach

no code implementations14 Dec 2022 Nam Phuong Tran, The-Anh Ta, Long Tran-Thanh

Using the side-observation approach, we prove an improved regret upper bound, which depends on the cardinality of the group, given that the group is finite.

Decision Making

Multi-Player Bandits Robust to Adversarial Collisions

no code implementations15 Nov 2022 Shivakumar Mahesh, Anshuka Rangi, Haifeng Xu, Long Tran-Thanh

We provide the first decentralized and robust algorithm RESYNC for defenders whose performance deteriorates gracefully as $\tilde{O}(C)$ as the number of collisions $C$ from the attackers increases.

Multi-Armed Bandits

Label driven Knowledge Distillation for Federated Learning with non-IID Data

no code implementations29 Sep 2022 Minh-Duong Nguyen, Quoc-Viet Pham, Dinh Thai Hoang, Long Tran-Thanh, Diep N. Nguyen, Won-Joo Hwang

Moreover, leveraging the advantages of hierarchical network design, we propose a new label-driven knowledge distillation (LKD) technique at the global server to address the second problem.

Federated Learning Knowledge Distillation

Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning

no code implementations29 Aug 2022 Anshuka Rangi, Haifeng Xu, Long Tran-Thanh, Massimo Franceschetti

To understand the security threats to reinforcement learning (RL) algorithms, this paper studies poisoning attacks to manipulate \emph{any} order-optimal learning algorithm towards a targeted policy in episodic RL and examines the potential damage of two natural types of poisoning attacks, i. e., the manipulation of \emph{reward} and \emph{action}.

reinforcement-learning reinforcement Learning

Learning to Represent Programs with Code Hierarchies

no code implementations31 May 2022 Minh H. Nguyen, Nghi D. Q. Bui, Truong Son Hy, Long Tran-Thanh, Risi Kondor

To address these issues, we propose a method for representing code as a hierarchy (Code Hierarchy), in which different code components are represented separately at various levels of granularity.

Clone Detection Code Classification +1

Temporal Multiresolution Graph Neural Networks For Epidemic Prediction

1 code implementation30 May 2022 Truong Son Hy, Viet Bach Nguyen, Long Tran-Thanh, Risi Kondor

In this paper, we introduce Temporal Multiresolution Graph Neural Networks (TMGNN), the first architecture that both learns to construct the multiscale and multiresolution graph structures and incorporates the time-series signals to capture the temporal changes of the dynamic graphs.

Graph Learning Time Series

Socialbots on Fire: Modeling Adversarial Behaviors of Socialbots via Multi-Agent Hierarchical Reinforcement Learning

no code implementations20 Oct 2021 Thai Le, Long Tran-Thanh, Dongwon Lee

To this question, we successfully demonstrate that indeed it is possible for adversaries to exploit computational learning mechanism such as reinforcement learning (RL) to maximize the influence of socialbots while avoiding being detected.

Adversarial Attack Hierarchical Reinforcement Learning +2

Online Markov Decision Processes with Non-oblivious Strategic Adversary

no code implementations7 Oct 2021 Le Cong Dinh, David Henry Mguni, Long Tran-Thanh, Jun Wang, Yaodong Yang

In this setting, we first demonstrate that MDP-Expert, an existing algorithm that works well with oblivious adversaries can still apply and achieve a policy regret bound of $\mathcal{O}(\sqrt{T \log(L)}+\tau^2\sqrt{ T \log(|A|)})$ where $L$ is the size of adversary's pure strategy set and $|A|$ denotes the size of agent's action space.

Topological Vanilla Transfer Learning

no code implementations29 Sep 2021 Nicholas George Bishop, Lau Truong Nguyen, Hieu Trung Thai, Thomas Davies, Long Tran-Thanh

In this paper we investigate the connection of topological similarity between source and target tasks with the efficiency of vanilla transfer learning (i. e., transfer learning without retraining) between them.

Transfer Learning

Incremental Training and Group Convolution Pruning for Runtime DNN Performance Scaling on Heterogeneous Embedded Platforms

no code implementations8 May 2021 Lei Xun, Long Tran-Thanh, Bashir M Al-Hashimi, Geoff V. Merrett

Compared to the existing works, our approach can provide up to 2. 36x (energy) and 2. 73x (time) wider dynamic range with a 2. 4x smaller memory footprint at the same compression rate.

Optimising Resource Management for Embedded Machine Learning

1 code implementation8 May 2021 Lei Xun, Long Tran-Thanh, Bashir M Al-Hashimi, Geoff V. Merrett

Machine learning inference is increasingly being executed locally on mobile and embedded platforms, due to the clear advantages in latency, privacy and connectivity.

BIG-bench Machine Learning Management

Saving Stochastic Bandits from Poisoning Attacks via Limited Data Verification

no code implementations15 Feb 2021 Anshuka Rangi, Long Tran-Thanh, Haifeng Xu, Massimo Franceschetti

In particular, for the case of unlimited verifications, we show that with $O(\log T)$ expected number of verifications, a simple modified version of the ETC type bandit algorithm can restore the order optimal $O(\log T)$ regret irrespective of the amount of contamination used by the attacker.

Data Poisoning

Sequential Choice Bandits with Feedback for Personalizing users' experience

no code implementations5 Jan 2021 Anshuka Rangi, Massimo Franceschetti, Long Tran-Thanh

We then propose bandit algorithms for the two feedback models and show that upper and lower bounds on the regret are of the order of $\tilde{O}(N^{2/3})$ and $\tilde\Omega(N^{2/3})$, respectively, where $N$ is the total number of users.

Optimal Learning from Verified Training Data

no code implementations NeurIPS 2020 Nicholas Bishop, Long Tran-Thanh, Enrico Gerding

In attempts to relax this assumption, fields such as adversarial learning typically assume that data is provided by an adversary, whose sole objective is to fool a learning algorithm.

Adversarial Blocking Bandits

no code implementations NeurIPS 2020 Nicholas Bishop, Hau Chan, Debmalya Mandal, Long Tran-Thanh

On the other hand, when B_T is not known, we show that the dynamic approximate regret of RGA-META is at most O((K+\tilde{D})^{1/4}\tilde{B}^{1/2}T^{3/4}) where \tilde{B} is the maximal path variation budget within each batch of RGA-META (which is provably in order of o(\sqrt{T}).

Hypothesis classes with a unique persistence diagram are NOT nonuniformly learnable

no code implementations NeurIPS Workshop TDA_and_Beyond 2020 Nicholas George Bishop, Thomas Davies, Long Tran-Thanh

The implicit role of a topological term in a loss function is to restrict the class of functions in which we are learning (the hypothesis class) to those with a specific topology.

Exploiting No-Regret Algorithms in System Design

no code implementations22 Jul 2020 Le Cong Dinh, Nick Bishop, Long Tran-Thanh

We investigate a repeated two-player zero-sum game setting where the column player is also a designer of the system, and has full control on the design of the payoff matrix.

Fuzzy c-Means Clustering for Persistence Diagrams

1 code implementation4 Jun 2020 Thomas Davies, Jack Aspinall, Bryan Wilder, Long Tran-Thanh

We end with experiments on two datasets that utilise both the topological and fuzzy nature of our algorithm: pre-trained model selection in machine learning and lattices structures from materials science.

BIG-bench Machine Learning Model Selection +1

Learning Optimal Temperature Region for Solving Mixed Integer Functional DCOPs

no code implementations27 Feb 2020 Saaduddin Mahmud, Md. Mosaddek Khan, Moumita Choudhury, Long Tran-Thanh, Nicholas R. Jennings

Distributed Constraint Optimization Problems (DCOPs) are an important framework for modeling coordinated decision-making problems in multi-agent systems with a set of discrete variables.

Decision Making

Path Planning Problems with Side Observations-When Colonels Play Hide-and-Seek

no code implementations19 Nov 2019 Dong Quan Vu, Patrick Loiseau, Alonso Silva, Long Tran-Thanh

Resource allocation games such as the famous Colonel Blotto (CB) and Hide-and-Seek (HS) games are often used to model a large variety of practical problems, but only in their one-shot versions.

Computer Science and Game Theory

Defending with Shared Resources on a Network

no code implementations19 Nov 2019 Minming Li, Long Tran-Thanh, Xiaowei Wu

For the case when defending resources cannot be shared, we present a max-flow-based exact algorithm.

AED: An Anytime Evolutionary DCOP Algorithm

no code implementations13 Sep 2019 Saaduddin Mahmud, Moumita Choudhury, Md. Mosaddek Khan, Long Tran-Thanh, Nicholas R. Jennings

Evolutionary optimization is a generic population-based metaheuristic that can be adapted to solve a wide variety of optimization problems and has proven very effective for combinatorial optimization problems.

Combinatorial Optimization

Manipulating a Learning Defender and Ways to Counteract

no code implementations NeurIPS 2019 Jiarui Gan, Qingyu Guo, Long Tran-Thanh, Bo An, Michael Wooldridge

We then apply a game-theoretic framework at a higher level to counteract such manipulation, in which the defender commits to a policy that specifies her strategy commitment according to the learned information.

Path Planning Problems with Side Observations-When Colonels Play Hide-and-Seek

2 code implementations27 May 2019 Dong Quan Vu, Patrick Loiseau, Alonso Silva, Long Tran-Thanh

Resource allocation games such as the famous Colonel Blotto (CB) and Hide-and-Seek (HS) games are often used to model a large variety of practical problems, but only in their one-shot versions.

Designing the Game to Play: Optimizing Payoff Structure in Security Games

no code implementations5 May 2018 Zheyuan Ryan Shi, Ziye Tang, Long Tran-Thanh, Rohit Singh, Fei Fang

We study Stackelberg Security Games where the defender, in addition to allocating defensive resources to protect targets from the attacker, can strategically manipulate the attacker's payoff under budget constraints in weighted L^p-norm form regarding the amount of change.

Efficiency of active learning for the allocation of workers on crowdsourced classification tasks

no code implementations19 Oct 2016 Edoardo Manino, Long Tran-Thanh, Nicholas R. Jennings

Crowdsourcing has been successfully employed in the past as an effective and cheap way to execute classification tasks and has therefore attracted the attention of the research community.

Active Learning General Classification

Functional Bandits

no code implementations10 May 2014 Long Tran-Thanh, Jia Yuan Yu

We introduce the functional bandit problem, where the objective is to find an arm that optimises a known functional of the unknown arm-reward distributions.

Decision Making Management

Bounding the Estimation Error of Sampling-based Shapley Value Approximation

1 code implementation18 Jun 2013 Sasan Maleki, Long Tran-Thanh, Greg Hines, Talal Rahwan, Alex Rogers

While this algorithm provides a bound on the approximation error, this bound is \textit{asymptotic}, meaning that it only holds when the number of samples increases to infinity.

Computer Science and Game Theory

Cannot find the paper you are looking for? You can Submit a new open access paper.