Search Results for author:
Found 38 papers, 7 papers with code
Bounding the Estimation Error of Sampling-based Shapley Value Approximation
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
Examining the Effects of Degree Distribution and Homophily in Graph Learning Models
In this work we examine how two additional synthetic graph generators can improve GraphWorld's evaluation; LFR, a well-established model in the graph clustering literature and CABAM, a recent adaptation of the Barabasi-Albert model tailored for GNN benchmarking.
Optimising Resource Management for Embedded Machine Learning
Machine learning inference is increasingly being executed locally on mobile and embedded platforms, due to the clear advantages in latency, privacy and connectivity.
Fuzzy c-Means Clustering for Persistence Diagrams
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.
Predicting COVID-19 pandemic by spatio-temporal graph neural networks: A New Zealand's study
In this work, we propose a novel deep learning architecture named Attention-based Multiresolution Graph Neural Networks (ATMGNN) that learns to combine the spatial graph information, i. e. geographical data, with the temporal information, i. e. timeseries data of number of COVID-19 cases, to predict the future dynamics of the pandemic.
Temporal Multiresolution Graph Neural Networks For Epidemic Prediction
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.
Designing the Game to Play: Optimizing Payoff Structure in Security Games
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
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.
Functional Bandits
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.
Efficient Thompson Sampling for Online Matrix-Factorization Recommendation
Matrix factorization (MF) collaborative filtering is an effective and widely used method in recommendation systems.
Path Planning Problems with Side Observations-When Colonels Play Hide-and-Seek
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.
Manipulating a Learning Defender and Ways to Counteract
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.
AED: An Anytime Evolutionary DCOP Algorithm
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.
Streaming Bayesian Inference for Crowdsourced Classification
Third, SBIC has provable asymptotic guarantees both in the online and offline settings.
Defending with Shared Resources on a Network
For the case when defending resources cannot be shared, we present a max-flow-based exact algorithm.
Path Planning Problems with Side Observations-When Colonels Play Hide-and-Seek
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
Learning Optimal Temperature Region for Solving Mixed Integer Functional DCOPs
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.
Exploiting No-Regret Algorithms in System Design
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.
Adversarial Blocking Bandits
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}).
Optimal Learning from Verified Training Data
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.
Sequential Choice Bandits with Feedback for Personalizing users' experience
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.
Saving Stochastic Bandits from Poisoning Attacks via Limited Data Verification
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.
Incremental Training and Group Convolution Pruning for Runtime DNN Performance Scaling on Heterogeneous Embedded Platforms
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.
Online Markov Decision Processes with Non-oblivious Strategic Adversary
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.
Expected Improvement-based Contextual Bandits
With a linear reward function, we demonstrate that our algorithm achieves a near-optimal regret.
Topological Vanilla Transfer Learning
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.
Socialbots on Fire: Modeling Adversarial Behaviors of Socialbots via Multi-Agent Hierarchical Reinforcement Learning
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.
Hypothesis classes with a unique persistence diagram are NOT nonuniformly learnable
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.
HierarchyNet: Learning to Summarize Source Code with Heterogeneous Representations
We propose a novel method for code summarization utilizing Heterogeneous Code Representations (HCRs) and our specially designed HierarchyNet.
Class Similarity Weighted Knowledge Distillation for Continual Semantic Segmentation
Our CSW-KD method distills the knowledge of a previous model on old classes that are similar to the new one.
Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning
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}.
Label driven Knowledge Distillation for Federated Learning with non-IID Data
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.
Multi-Player Bandits Robust to Adversarial Collisions
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.
Invariant Lipschitz Bandits: A Side Observation Approach
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.
Achieving Better Regret against Strategic Adversaries
We study online learning problems in which the learner has extra knowledge about the adversary's behaviour, i. e., in game-theoretic settings where opponents typically follow some no-external regret learning algorithms.
Revisiting LARS for Large Batch Training Generalization of Neural Networks
This paper explores Large Batch Training techniques using layer-wise adaptive scaling ratio (LARS) across diverse settings, uncovering insights.
Learning the Expected Core of Strictly Convex Stochastic Cooperative Games
Reward allocation, also known as the credit assignment problem, has been an important topic in economics, engineering, and machine learning.
Betting on what is neither verifiable nor falsifiable
Prediction markets are useful for estimating probabilities of claims whose truth will be revealed at some fixed time -- this includes questions about the values of real-world events (i. e. statistical uncertainty), and questions about the values of primitive recursive functions (i. e. logical or algorithmic uncertainty).
