Long Tran-Thanh

Phurinut Srisawad, Juergen Branke, Long Tran-Thanh

We study payoff manipulation in repeated multi-objective Stackelberg games, where a leader may strategically influence a follower's deterministic best response, e.g., by offering a share of their own payoff. We assume that the follower's utility function, representing preferences over multiple objectives, is unknown but linear, and its weight parameter must be inferred through interaction. This introduces a sequential decision-making challenge for the leader, who must balance preference elicitation with immediate utility maximisation. We formalise this problem and propose manipulation policies based on expected utility (EU) and long-term expected utility (longEU), which guide the leader in selecting actions and offering incentives that trade off short-term gains with long-term impact. We prove that under infinite repeated interactions, longEU converges to the optimal manipulation. Empirical results across benchmark environments demonstrate that our approach improves cumulative leader utility while promoting mutually beneficial outcomes, all without requiring explicit negotiation or prior knowledge of the follower's utility function.

Anshuka Rangi, Haifeng Xu, Long Tran-Thanh et al.

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}. We discover that the effect of attacks crucially depend on whether the rewards are bounded or unbounded. In bounded reward settings, we show that only reward manipulation or only action manipulation cannot guarantee a successful attack. However, by combining reward and action manipulation, the adversary can manipulate any order-optimal learning algorithm to follow any targeted policy with $\tildeΘ(\sqrt{T})$ total attack cost, which is order-optimal, without any knowledge of the underlying MDP. In contrast, in unbounded reward settings, we show that reward manipulation attacks are sufficient for an adversary to successfully manipulate any order-optimal learning algorithm to follow any targeted policy using $\tilde{O}(\sqrt{T})$ amount of contamination. Our results reveal useful insights about what can or cannot be achieved by poisoning attacks, and are set to spur more works on the design of robust RL algorithms.

Khoi Do, Duong Nguyen, Hoa Nguyen et al.

This paper explores Large Batch Training techniques using layer-wise adaptive scaling ratio (LARS) across diverse settings, uncovering insights. LARS algorithms with warm-up tend to be trapped in sharp minimizers early on due to redundant ratio scaling. Additionally, a fixed steep decline in the latter phase restricts deep neural networks from effectively navigating early-phase sharp minimizers. Building on these findings, we propose Time Varying LARS (TVLARS), a novel algorithm that replaces warm-up with a configurable sigmoid-like function for robust training in the initial phase. TVLARS promotes gradient exploration early on, surpassing sharp optimizers and gradually transitioning to LARS for robustness in later phases. Extensive experiments demonstrate that TVLARS consistently outperforms LARS and LAMB in most cases, with up to 2\% improvement in classification scenarios. Notably, in all self-supervised learning cases, TVLARS dominates LARS and LAMB with performance improvements of up to 10\%.

Minh-Duong Nguyen, Quoc-Viet Pham, Dinh Thai Hoang et al.

In real-world applications, Federated Learning (FL) meets two challenges: (1) scalability, especially when applied to massive IoT networks; and (2) how to be robust against an environment with heterogeneous data. Realizing the first problem, we aim to design a novel FL framework named Full-stack FL (F2L). More specifically, F2L utilizes a hierarchical network architecture, making extending the FL network accessible without reconstructing the whole network system. 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. As opposed to current knowledge distillation techniques, LKD is capable of training a student model, which consists of good knowledge from all teachers' models. Therefore, our proposed algorithm can effectively extract the knowledge of the regions' data distribution (i.e., the regional aggregated models) to reduce the divergence between clients' models when operating under the FL system with non-independent identically distributed data. Extensive experiment results reveal that: (i) our F2L method can significantly improve the overall FL efficiency in all global distillations, and (ii) F2L rapidly achieves convergence as global distillation stages occur instead of increasing on each communication cycle.

Truong Son Hy, Viet Bach Nguyen, Long Tran-Thanh et al.

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. We have applied our proposed model to the task of predicting future spreading of epidemic and pandemic based on the historical time-series data collected from the actual COVID-19 pandemic and chickenpox epidemic in several European countries, and have obtained competitive results in comparison to other previous state-of-the-art temporal architectures and graph learning algorithms. We have shown that capturing the multiscale and multiresolution structures of graphs is important to extract either local or global information that play a critical role in understanding the dynamic of a global pandemic such as COVID-19 which started from a local city and spread to the whole world. Our work brings a promising research direction in forecasting and mitigating future epidemics and pandemics.

Mustafa Yasir, John Palowitch, Anton Tsitsulin et al.

Despite a surge in interest in GNN development, homogeneity in benchmarking datasets still presents a fundamental issue to GNN research. GraphWorld is a recent solution which uses the Stochastic Block Model (SBM) to generate diverse populations of synthetic graphs for benchmarking any GNN task. Despite its success, the SBM imposed fundamental limitations on the kinds of graph structure GraphWorld could create. 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. By integrating these generators, we significantly expand the coverage of graph space within the GraphWorld framework while preserving key graph properties observed in real-world networks. To demonstrate their effectiveness, we generate 300,000 graphs to benchmark 11 GNN models on a node classification task. We find GNN performance variations in response to homophily, degree distribution and feature signal. Based on these findings, we classify models by their sensitivity to the new generators under these properties. Additionally, we release the extensions made to GraphWorld on the GitHub repository, offering further evaluation of GNN performance on new graphs.

Minh Huynh Nguyen, Nghi D. Q. Bui, Truong Son Hy et al.

We propose a novel method for code summarization utilizing Heterogeneous Code Representations (HCRs) and our specially designed HierarchyNet. HCRs effectively capture essential code features at lexical, syntactic, and semantic levels by abstracting coarse-grained code elements and incorporating fine-grained program elements in a hierarchical structure. Our HierarchyNet method processes each layer of the HCR separately through a unique combination of the Heterogeneous Graph Transformer, a Tree-based CNN, and a Transformer Encoder. This approach preserves dependencies between code elements and captures relations through a novel Hierarchical-Aware Cross Attention layer. Our method surpasses current state-of-the-art techniques, such as PA-Former, CAST, and NeuralCodeSum.

Shivakumar Mahesh, Anshuka Rangi, Haifeng Xu et al.

Motivated by cognitive radios, stochastic Multi-Player Multi-Armed Bandits has been extensively studied in recent years. In this setting, each player pulls an arm, and receives a reward corresponding to the arm if there is no collision, namely the arm was selected by one single player. Otherwise, the player receives no reward if collision occurs. In this paper, we consider the presence of malicious players (or attackers) who obstruct the cooperative players (or defenders) from maximizing their rewards, by deliberately colliding with them. 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. We show that this algorithm is order-optimal by proving a lower bound which scales as $Ω(C)$. This algorithm is agnostic to the algorithm used by the attackers and agnostic to the number of collisions $C$ faced from attackers.

Nam Phuong Tran, Andi Nika, Goran Radanovic et al.

We investigate robustness to strong data corruption in offline sparse reinforcement learning (RL). In our setting, an adversary may arbitrarily perturb a fraction of the collected trajectories from a high-dimensional but sparse Markov decision process, and our goal is to estimate a near optimal policy. The main challenge is that, in the high-dimensional regime where the number of samples $N$ is smaller than the feature dimension $d$, exploiting sparsity is essential for obtaining non-vacuous guarantees but has not been systematically studied in offline RL. We analyse the problem under uniform coverage and sparse single-concentrability assumptions. While Least Square Value Iteration (LSVI), a standard approach for robust offline RL, performs well under uniform coverage, we show that integrating sparsity into LSVI is unnatural, and its analysis may break down due to overly pessimistic bonuses. To overcome this, we propose actor-critic methods with sparse robust estimator oracles, which avoid the use of pointwise pessimistic bonuses and provide the first non-vacuous guarantees for sparse offline RL under single-policy concentrability coverage. Moreover, we extend our results to the contaminated setting and show that our algorithm remains robust under strong contamination. Our results provide the first non-vacuous guarantees in high-dimensional sparse MDPs with single-policy concentrability coverage and corruption, showing that learning a near-optimal policy remains possible in regimes where traditional robust offline RL techniques may fail.

Le Cong Dinh, Tri-Dung Nguyen, Alain Zemkoho et al.

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. Under this assumption, we propose two new online learning algorithms, Accurate Follow the Regularized Leader (AFTRL) and Prod-Best Response (Prod-BR), that intensively exploit this extra knowledge while maintaining the no-regret property in the worst-case scenario of having inaccurate extra information. Specifically, AFTRL achieves $O(1)$ external regret or $O(1)$ \emph{forward regret} against no-external regret adversary in comparison with $O(\sqrt{T})$ \emph{dynamic regret} of Prod-BR. To the best of our knowledge, our algorithm is the first to consider forward regret that achieves $O(1)$ regret against strategic adversaries. When playing zero-sum games with Accurate Multiplicative Weights Update (AMWU), a special case of AFTRL, we achieve \emph{last round convergence} to the Nash Equilibrium. We also provide numerical experiments to further support our theoretical results. In particular, we demonstrate that our methods achieve significantly better regret bounds and rate of last round convergence, compared to the state of the art (e.g., Multiplicative Weights Update (MWU) and its optimistic counterpart, OMWU).

Nam Phuong Tran, Long Tran-Thanh

Symmetry arises in many optimization and decision-making problems, and has attracted considerable attention from the optimization community: By utilizing the existence of such symmetries, the process of searching for optimal solutions can be improved significantly. Despite its success in (offline) optimization, the utilization of symmetries has not been well examined within the online optimization settings, especially in the bandit literature. As such, in this paper we study the invariant Lipschitz bandit setting, a subclass of the Lipschitz bandits where the reward function and the set of arms are preserved under a group of transformations. We introduce an algorithm named \texttt{UniformMesh-N}, which naturally integrates side observations using group orbits into the \texttt{UniformMesh} algorithm (\cite{Kleinberg2005_UniformMesh}), which uniformly discretizes the set of arms. 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. We also prove a matching regret's lower bound for the invariant Lipschitz bandit class (up to logarithmic factors). We hope that our work will ignite further investigation of symmetry in bandit theory and sequential decision-making theory in general.

Phu-Quy Nguyen-Lam, Phu-Hoa Pham, Dao Sy Duy Minh et al.

Object-centric representations promise a key property for few-shot learning: Rather than treating a scene as a single unit, a model can decompose it into individual object-level parts that can be matched and compared across different concepts. In practice, this potential is rarely realized. Continual learners either collapse scenes into global embeddings, or train with part-level matching objectives that tie representations too closely to seen patterns, leaving them unable to generalize to truly novel concepts. In this paper, we identify this fundamental structural conflict and pioneer a new paradigm that strictly decouples representation learning from compositional inference. Leveraging the inherent patch-level semantic geometry of self-supervised Vision Transformers (ViTs), our framework employs a dual-phase strategy. During training, slot representations are optimized entirely toward holistic class identity, preserving highly generalizable, object-level geometries. At inference, preserved slots are dynamically composed to match novel scenes. We demonstrate that this paradigm offers dual structural benefits: The frozen backbone naturally prevents representation drift, while our lightweight, holistic optimization preserves the features' capacity for novel-concept transfer. Extensive experiments validate this approach, achieving state-of-the-art unseen-concept generalization and minimal forgetting across standard continual learning benchmarks.

Phu-Hoa Pham, Chi-Nguyen Tran, Nguyen Lam Phu Quy et al.

Streaming decision trees are natural candidates for open-world continual learning, as they perform local updates, enjoy bounded memory, and static decision boundaries. Despite these, they still fail in online class-incremental learning due to two coupled miscalibrations: (i) their split criterion grows unreliable as the class count K expands, and (ii) the absence of knowledge transfer at split time. Both failures share a common root: the range of Information Gain intrinsically scales with log2 K. Consequently, any Hoeffding-style confidence radius derived from it must inevitably grow with the class count, making a K-independent split criterion structurally impossible, taking away the potential benefits of applying streaming decision trees to continual learning. To fix this issue, we present MIST (McDiarmid Incremental Streaming Tree), which resolves both failures through three integrated components: (i) a tight, K-independent McDiarmid confidence radius for Gini splitting that acts as a structural regulariser; (ii) a Bayesian inheritance protocol that projects parent statistics to child nodes via truncated-Gaussian moments, with variance reduction guarantees strongest precisely when splitting is most conservative; and (iii) per-leaf KLL quantile sketches that support both continuous threshold evaluation and geometry-adaptive leaf prediction from a single data structure. On standard and stress-test tabular streams, MIST is competitive with global parametric methods on near-Gaussian benchmarks and uniquely robust on non-Gaussian geometry where SOTA benchmarks collapse.

Chi-Nguyen Tran, Dao Sy Duy Minh, Huynh Trung Kiet et al.

Cross-view geo-localization (CVGL), which matches an oblique drone view to a geo-referenced satellite tile, has emerged as a key alternative for autonomous drone navigation when GNSS signals are jammed, spoofed, or unavailable. Despite strong recent progress, three limitations persist: (1) global-descriptor designs compress the patch grid into a single vector without separating layout from texture across the view gap; (2) altitude-related scale variation is retained in the learned embedding rather than marginalized; and (3) multi-objective training relies on hand-tuned scalars over losses on incompatible gradient scales. We propose SkyPart, a lightweight swappable head for patch-based vision transformers (ViTs) that institutes explicit part grouping over the patch grid. SkyPart has four theory-grounded components: (i) learnable prototypes competing for patch tokens via single-pass cosine assignment; (ii) altitude-conditioned linear modulation applied only during training, making the retrieval embedding altitude-free at inference; (iii) a graph-attention readout over active prototypes; and (iv) a Kendall uncertainty-weighted multi-objective loss whose stationary points are Pareto-stationary. At 26.95M parameters and 22.14 GFLOPs, SkyPart is the smallest among top-performing methods and sets a new state of the art on SUES-200, University-1652, and DenseUAV under a single-pass, no-re-ranking, no-TTA protocol. Its advantage over the strongest baseline widens under the ten-condition WeatherPrompt corruption benchmark.

Huynh Trung Kiet, Dao Sy Duy Minh, Tuan Nguyen et al.

Large language models increasingly mediate decisions that turn on moral judgement, yet a growing body of evidence shows that their implicit preferences are not culturally neutral. Existing cultural alignment methods either require per-country preference data and fine-tuning budgets or assume white-box access to model internals that commercial APIs do not expose. In this work, we focus on this realistic black-box, public-data-only regime and observe that within-country sociodemographic disagreement, not consensus, is the primary steering signal. We introduce DISCA (Disagreement-Informed Steering for Cultural Alignment), an inference-time method that instantiates each country as a panel of World-Values-Survey-grounded persona agents and converts their disagreement into a bounded, loss-averse logit correction. Across 20 countries and 7 open-weight backbones (2B--70B), DISCA reduces cultural misalignment on MultiTP by 10--24% on the six backbones >=3.8B, and 2--7% on open-ended scenarios, without changing any weights. Our results suggest that inference-time calibration is a scalable alternative to fine-tuning for serving the long tail of global moral preferences.

Viet Bach Nguyen, Truong Son Hy, Long Tran-Thanh et al.

Modeling and simulations of pandemic dynamics play an essential role in understanding and addressing the spreading of highly infectious diseases such as COVID-19. 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. The key innovation is that our method can capture the multiscale structures of the spatial graph via a learning to cluster algorithm in a data-driven manner. This allows our architecture to learn to pick up either local or global signals of a pandemic, and model both the long-range spatial and temporal dependencies. Importantly, we collected and assembled a new dataset for New Zealand. We established a comprehensive benchmark of statistical methods, temporal architectures, graph neural networks along with our spatio-temporal model. We also incorporated socioeconomic cross-sectional data to further enhance our prediction. Our proposed model have shown highly robust predictions and outperformed all other baselines in various metrics for our new dataset of New Zealand along with existing datasets of England, France, Italy and Spain. For a future work, we plan to extend our work for real-time prediction and global scale. Our data and source code are publicly available at https://github.com/HySonLab/pandemic_tgnn

Abhimanyu Pallavi Sudhir, Long Tran-Thanh

One of the impediments to the efficiency of information markets is the inherent information asymmetry present in them, exacerbated by the "buyer's inspection paradox" (the buyer cannot mitigate the asymmetry by "inspecting" the information, because in doing so the buyer obtains the information without paying for it). Previous work has suggested that using Large Language Model (LLM) buyers to inspect and purchase information could overcome this information asymmetry, as an LLM buyer can simply "forget" the information it inspects. In this work, we analyze this mechanism formally through a "value-of-information" paradigm, i.e. whether it incentivizes information to be priced and provided in accordance with its "true value". We focus in particular on our new recursive version of the mechanism, which we believe has a range of applications including in AI alignment research, where it is related to Extrapolated Volition and Scalable Oversight.

Hoang Pham, The-Anh Ta, Long Tran-Thanh

Pruning at Initialisation methods discover sparse, trainable subnetworks before training, but their theoretical mechanisms remain elusive. Existing analyses are often limited to finite-width statistics, lacking a rigorous characterisation of the global sparsity patterns that emerge as networks grow large. In this work, we connect discrete pruning heuristics to graph limit theory via graphons, establishing the graphon limit of PaI masks. We introduce a Factorised Saliency Model that encompasses popular pruning criteria and prove that, under regularity conditions, the discrete masks generated by these algorithms converge to deterministic bipartite graphons. This limit framework establishes a novel topological taxonomy for sparse networks: while unstructured methods (e.g., Random, Magnitude) converge to homogeneous graphons representing uniform connectivity, data-driven methods (e.g., SNIP, GraSP) converge to heterogeneous graphons that encode implicit feature selection. Leveraging this continuous characterisation, we derive two fundamental theoretical results: (i) a Universal Approximation Theorem for sparse networks that depends only on the intrinsic dimension of active coordinate subspaces; and (ii) a Graphon-NTK generalisation bound demonstrating how the limit graphon modulates the kernel geometry to align with informative features. Our results transform the study of sparse neural networks from combinatorial graph problems into a rigorous framework of continuous operators, offering a new mechanism for analysing expressivity and generalisation in sparse neural networks.

Phurinut Srisawad, Juergen Branke, Long Tran-Thanh

This paper formulates a new Best-Arm Identification problem in the non-stationary stochastic bandits setting, where the means of all arms are shifted in the same way due to a global influence of the environment. The aim is to identify the unique best arm across environmental change given a fixed total budget. While this setting can be regarded as a special case of Adversarial Bandits or Corrupted Bandits, we demonstrate that existing solutions tailored to those settings do not fully utilise the nature of this global influence, and thus, do not work well in practice (despite their theoretical guarantees). To overcome this issue, in this paper we develop a novel selection policy that is consistent and robust in dealing with global environmental shifts. We then propose an allocation policy, LinLUCB, which exploits information about global shifts across all arms in each environment. Empirical tests depict a significant improvement in our policies against other existing methods.

Lan-Cuong Nguyen, Quan Nguyen-Tri, Bang Tran Khanh et al.

Few-shot image classification remains challenging due to the scarcity of labeled training examples. Augmenting them with synthetic data has emerged as a promising way to alleviate this issue, but models trained on synthetic samples often face performance degradation due to the inherent gap between real and synthetic distributions. To address this limitation, we develop a theoretical framework that quantifies the impact of such distribution discrepancies on supervised learning, specifically in the context of image classification. More importantly, our framework suggests practical ways to generate good synthetic samples and to train a predictor with high generalization ability. Building upon this framework, we propose a novel theoretical-based algorithm that integrates prototype learning to optimize both data partitioning and model training, effectively bridging the gap between real few-shot data and synthetic data. Extensive experiments results show that our approach demonstrates superior performance compared to state-of-the-art methods, outperforming them across multiple datasets.

Nam Phuong Tran, The Anh Ta, Debmalya Mandal et al.

High-dimensional linear bandits with low-dimensional structure have received considerable attention in recent studies due to their practical significance. The most common structure in the literature is sparsity. However, it may not be available in practice. Symmetry, where the reward is invariant under certain groups of transformations on the set of arms, is another important inductive bias in the high-dimensional case that covers many standard structures, including sparsity. In this work, we study high-dimensional symmetric linear bandits where the symmetry is hidden from the learner, and the correct symmetry needs to be learned in an online setting. We examine the structure of a collection of hidden symmetry and provide a method based on model selection within the collection of low-dimensional subspaces. Our algorithm achieves a regret bound of $ O(d_0^{2/3} T^{2/3} \log(d))$, where $d$ is the ambient dimension which is potentially very large, and $d_0$ is the dimension of the true low-dimensional subspace such that $d_0 \ll d$. With an extra assumption on well-separated models, we can further improve the regret to $ O(d_0\sqrt{T\log(d)} )$.

Hoang Pham, The-Anh Ta, Tom Jacobs et al.

Sparse neural networks promise efficiency, yet training them effectively remains a fundamental challenge. Despite advances in pruning methods that create sparse architectures, understanding why some sparse structures are better trainable than others with the same level of sparsity remains poorly understood. Aiming to develop a systematic approach to this fundamental problem, we propose a novel theoretical framework based on the theory of graph limits, particularly graphons, that characterizes sparse neural networks in the infinite-width regime. Our key insight is that connectivity patterns of sparse neural networks induced by pruning methods converge to specific graphons as networks' width tends to infinity, which encodes implicit structural biases of different pruning methods. We postulate the Graphon Limit Hypothesis and provide empirical evidence to support it. Leveraging this graphon representation, we derive a Graphon Neural Tangent Kernel (Graphon NTK) to study the training dynamics of sparse networks in the infinite width limit. Graphon NTK provides a general framework for the theoretical analysis of sparse networks. We empirically show that the spectral analysis of Graphon NTK correlates with observed training dynamics of sparse networks, explaining the varying convergence behaviours of different pruning methods. Our framework provides theoretical insights into the impact of connectivity patterns on the trainability of various sparse network architectures.

Tuan Nguyen, Long Tran-Thanh

Ensuring that large language models (LLMs) comply with safety requirements is a central challenge in AI deployment. Existing alignment approaches primarily operate during training, such as through fine-tuning or reinforcement learning from human feedback, but these methods are costly and inflexible, requiring retraining whenever new requirements arise. Recent efforts toward inference-time alignment mitigate some of these limitations but still assume access to model internals, which is impractical, and not suitable for third party stakeholders who do not have access to the models. In this work, we propose a model-independent, black-box framework for safety alignment that does not require retraining or access to the underlying LLM architecture. As a proof of concept, we address the problem of trading off between generating safe but uninformative answers versus helpful yet potentially risky ones. We formulate this dilemma as a two-player zero-sum game whose minimax equilibrium captures the optimal balance between safety and helpfulness. LLM agents operationalize this framework by leveraging a linear programming solver at inference time to compute equilibrium strategies. Our results demonstrate the feasibility of black-box safety alignment, offering a scalable and accessible pathway for stakeholders, including smaller organizations and entities in resource-constrained settings, to enforce safety across rapidly evolving LLM ecosystems.

Abhimanyu Pallavi Sudhir, Long Tran-Thanh

Market-based agents refer to reinforcement learning agents which determine their actions based on an internal market of sub-agents. We introduce a new type of market-based algorithm where the state itself is factored into several axes called ``goods'', which allows for greater specialization and parallelism than existing market-based RL algorithms. Furthermore, we argue that market-based algorithms have the potential to address many current challenges in AI, such as search, dynamic scaling and complete feedback, and demonstrate that they may be seen to generalize neural networks; finally, we list some novel ways that market algorithms may be applied in conjunction with Large Language Models for immediate practical applicability.

Nam Phuong Tran, The Anh Ta, Shuqing Shi et al.

Reward allocation, also known as the credit assignment problem, has been an important topic in economics, engineering, and machine learning. An important concept in reward allocation is the core, which is the set of stable allocations where no agent has the motivation to deviate from the grand coalition. In previous works, computing the core requires either knowledge of the reward function in deterministic games or the reward distribution in stochastic games. However, this is unrealistic, as the reward function or distribution is often only partially known and may be subject to uncertainty. In this paper, we consider the core learning problem in stochastic cooperative games, where the reward distribution is unknown. Our goal is to learn the expected core, that is, the set of allocations that are stable in expectation, given an oracle that returns a stochastic reward for an enquired coalition each round. Within the class of strictly convex games, we present an algorithm named \texttt{Common-Points-Picking} that returns a point in the expected core given a polynomial number of samples, with high probability. To analyse the algorithm, we develop a new extension of the separation hyperplane theorem for multiple convex sets.

Abhimanyu Pallavi Sudhir, Long Tran-Thanh

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). However, they cannot be directly applied to questions without a fixed resolution criterion, and real-world applications of prediction markets to such questions often amount to predicting not whether a sentence is true, but whether it will be proven. Such questions could be represented by countable unions or intersections of more basic events, or as First-Order-Logic sentences on the Arithmetical Hierarchy (or even beyond FOL, as hyperarithmetical sentences). In this paper, we propose an approach to betting on such events via options, or equivalently as bets on the outcome of a "verification-falsification game". Our work thus acts as an alternative to the existing framework of Garrabrant induction for logical uncertainty, and relates to the stance known as constructivism in the philosophy of mathematics; furthermore it has broader implications for philosophy and mathematical logic.

Thai Le, Long Tran-Thanh, Dongwon Lee

Socialbots are software-driven user accounts on social platforms, acting autonomously (mimicking human behavior), with the aims to influence the opinions of other users or spread targeted misinformation for particular goals. As socialbots undermine the ecosystem of social platforms, they are often considered harmful. As such, there have been several computational efforts to auto-detect the socialbots. However, to our best knowledge, the adversarial nature of these socialbots has not yet been studied. This begs a question "can adversaries, controlling socialbots, exploit AI techniques to their advantage?" 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. We first formulate the adversarial socialbot learning as a cooperative game between two functional hierarchical RL agents. While one agent curates a sequence of activities that can avoid the detection, the other agent aims to maximize network influence by selectively connecting with right users. Our proposed policy networks train with a vast amount of synthetic graphs and generalize better than baselines on unseen real-life graphs both in terms of maximizing network influence (up to +18%) and sustainable stealthiness (up to +40% undetectability) under a strong bot detector (with 90% detection accuracy). During inference, the complexity of our approach scales linearly, independent of a network's structure and the virality of news. This makes our approach a practical adversarial attack when deployed in a real-life setting.

Le Cong Dinh, David Henry Mguni, Long Tran-Thanh et al.

We study a novel setting in Online Markov Decision Processes (OMDPs) where the loss function is chosen by a non-oblivious strategic adversary who follows a no-external regret algorithm. 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 $\mathcal{O}(\sqrt{T \log(L)}+τ^2\sqrt{ T \log(|A|)})$ where $L$ is the size of adversary's pure strategy set and $|A|$ denotes the size of agent's action space. Considering real-world games where the support size of a NE is small, we further propose a new algorithm: MDP-Online Oracle Expert (MDP-OOE), that achieves a policy regret bound of $\mathcal{O}(\sqrt{T\log(L)}+τ^2\sqrt{ T k \log(k)})$ where $k$ depends only on the support size of the NE. MDP-OOE leverages the key benefit of Double Oracle in game theory and thus can solve games with prohibitively large action space. Finally, to better understand the learning dynamics of no-regret methods, under the same setting of no-external regret adversary in OMDPs, we introduce an algorithm that achieves last-round convergence result to a NE. To our best knowledge, this is first work leading to the last iteration result in OMDPs.

Lei Xun, Long Tran-Thanh, Bashir M Al-Hashimi et al.

Machine learning inference is increasingly being executed locally on mobile and embedded platforms, due to the clear advantages in latency, privacy and connectivity. In this paper, we present approaches for online resource management in heterogeneous multi-core systems and show how they can be applied to optimise the performance of machine learning workloads. Performance can be defined using platform-dependent (e.g. speed, energy) and platform-independent (accuracy, confidence) metrics. In particular, we show how a Deep Neural Network (DNN) can be dynamically scalable to trade-off these various performance metrics. Achieving consistent performance when executing on different platforms is necessary yet challenging, due to the different resources provided and their capability, and their time-varying availability when executing alongside other workloads. Managing the interface between available hardware resources (often numerous and heterogeneous in nature), software requirements, and user experience is increasingly complex.

Lei Xun, Long Tran-Thanh, Bashir M Al-Hashimi et al.

Inference for Deep Neural Networks is increasingly being executed locally on mobile and embedded platforms due to its advantages in latency, privacy and connectivity. Since modern System on Chips typically execute a combination of different and dynamic workloads concurrently, it is challenging to consistently meet inference time/energy budget at runtime because of the local computing resources available to the DNNs vary considerably. To address this challenge, a variety of dynamic DNNs were proposed. However, these works have significant memory overhead, limited runtime recoverable compression rate and narrow dynamic ranges of performance scaling. In this paper, we present a dynamic DNN using incremental training and group convolution pruning. The channels of the DNN convolution layer are divided into groups, which are then trained incrementally. At runtime, following groups can be pruned for inference time/energy reduction or added back for accuracy recovery without model retraining. In addition, we combine task mapping and Dynamic Voltage Frequency Scaling (DVFS) with our dynamic DNN to deliver finer trade-off between accuracy and time/power/energy over a wider dynamic range. We illustrate the approach by modifying AlexNet for the CIFAR10 image dataset and evaluate our work on two heterogeneous hardware platforms: Odroid XU3 (ARM big.LITTLE CPUs) and Nvidia Jetson Nano (CPU and GPU). 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. It achieved 10.6x (energy) and 41.6x (time) wider dynamic range by combining with task mapping and DVFS.

Anshuka Rangi, Long Tran-Thanh, Haifeng Xu et al.

We study bandit algorithms under data poisoning attacks in a bounded reward setting. We consider a strong attacker model in which the attacker can observe both the selected actions and their corresponding rewards and can contaminate the rewards with additive noise. We show that any bandit algorithm with regret $O(\log T)$ can be forced to suffer a regret $Ω(T)$ with an expected amount of contamination $O(\log T)$. This amount of contamination is also necessary, as we prove that there exists an $O(\log T)$ regret bandit algorithm, specifically the classical UCB, that requires $Ω(\log T)$ amount of contamination to suffer regret $Ω(T)$. To combat such attacks, our second main contribution is to propose verification based mechanisms, which use limited verification to access a limited number of uncontaminated rewards. 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. We also provide a UCB-like verification scheme, called Secure-UCB, that also enjoys full recovery from any attacks, also with $O(\log T)$ expected number of verifications. To derive a matching lower bound on the number of verifications, we prove that for any order-optimal bandit algorithm, this number of verifications $Ω(\log T)$ is necessary to recover the order-optimal regret. On the other hand, when the number of verifications is bounded above by a budget $B$, we propose a novel algorithm, Secure-BARBAR, which provably achieves $O(\min\{C,T/\sqrt{B} \})$ regret with high probability against weak attackers where $C$ is the total amount of contamination by the attacker, which breaks the known $Ω(C)$ lower bound of the non-verified setting if $C$ is large.

Anshuka Rangi, Massimo Franceschetti, Long Tran-Thanh

In this work, we study sequential choice bandits with feedback. We propose bandit algorithms for a platform that personalizes users' experience to maximize its rewards. For each action directed to a given user, the platform is given a positive reward, which is a non-decreasing function of the action, if this action is below the user's threshold. Users are equipped with a patience budget, and actions that are above the threshold decrease the user's patience. When all patience is lost, the user abandons the platform. The platform attempts to learn the thresholds of the users in order to maximize its rewards, based on two different feedback models describing the information pattern available to the platform at each action. We define a notion of regret by determining the best action to be taken when the platform knows that the user's threshold is in a given interval. 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 $\tildeΩ(N^{2/3})$, respectively, where $N$ is the total number of users. Finally, we show that the waiting time of any user before receiving a personalized experience is uniform in $N$.

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. In addition, the row player uses a no-regret algorithm to efficiently learn how to adapt their strategy to the column player's behaviour over time in order to achieve good total payoff. The goal of the column player is to guide her opponent to pick a mixed strategy which is favourable for the system designer. Therefore, she needs to: (i) design an appropriate payoff matrix $A$ whose unique minimax solution contains the desired mixed strategy of the row player; and (ii) strategically interact with the row player during a sequence of plays in order to guide her opponent to converge to that desired behaviour. To design such a payoff matrix, we propose a novel solution that provably has a unique minimax solution with the desired behaviour. We also investigate a relaxation of this problem where uniqueness is not required, but all the minimax solutions have the same mixed strategy for the row player. Finally, we propose a new game playing algorithm for the system designer and prove that it can guide the row player, who may play a \emph{stable} no-regret algorithm, to converge to a minimax solution.

Thomas Davies, Jack Aspinall, Bryan Wilder et al.

Persistence diagrams concisely represent the topology of a point cloud whilst having strong theoretical guarantees, but the question of how to best integrate this information into machine learning workflows remains open. In this paper we extend the ubiquitous Fuzzy c-Means (FCM) clustering algorithm to the space of persistence diagrams, enabling unsupervised learning that automatically captures the topological structure of data without the topological prior knowledge or additional processing of persistence diagrams that many other techniques require. We give theoretical convergence guarantees that correspond to the Euclidean case, and empirically demonstrate the capability of our algorithm to capture topological information via the fuzzy RAND index. 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. As pre-trained models can perform well on multiple tasks, selecting the best model is a naturally fuzzy problem; we show that fuzzy clustering persistence diagrams allows for model selection using the topology of decision boundaries. In materials science, we classify transformed lattice structure datasets for the first time, whilst the probabilistic membership values let us rank candidate lattices in a scenario where further investigation requires expensive laboratory time and expertise.

Saaduddin Mahmud, Md. Mosaddek Khan, Moumita Choudhury et al.

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. Later works have extended DCOPs to model problems with a set of continuous variables, named Functional DCOPs (F-DCOPs). In this paper, we combine both of these frameworks into the Mixed Integer Functional DCOP (MIF-DCOP) framework that can deal with problems regardless of their variables' type. We then propose a novel algorithm $-$ Distributed Parallel Simulated Annealing (DPSA), where agents cooperatively learn the optimal parameter configuration for the algorithm while also solving the given problem using the learned knowledge. Finally, we empirically evaluate our approach in DCOP, F-DCOP, and MIF-DCOP settings and show that DPSA produces solutions of significantly better quality than the state-of-the-art non-exact algorithms in their corresponding settings.

Minming Li, Long Tran-Thanh, Xiaowei Wu

In this paper we consider a defending problem on a network. In the model, the defender holds a total defending resource of R, which can be distributed to the nodes of the network. The defending resource allocated to a node can be shared by its neighbors. There is a weight associated with every edge that represents the efficiency defending resources are shared between neighboring nodes. We consider the setting when each attack can affect not only the target node, but its neighbors as well. Assuming that nodes in the network have different treasures to defend and different defending requirements, the defender aims at allocating the defending resource to the nodes to minimize the loss due to attack. We give polynomial time exact algorithms for two important special cases of the network defending problem. For the case when an attack can only affect the target node, we present an LP-based exact algorithm. For the case when defending resources cannot be shared, we present a max-flow-based exact algorithm. We show that the general problem is NP-hard, and we give a 2-approximation algorithm based on LP-rounding. Moreover, by giving a matching lower bound of 2 on the integrality gap on the LP relaxation, we show that our rounding is tight.

Edoardo Manino, Long Tran-Thanh, Nicholas R. Jennings

A key challenge in crowdsourcing is inferring the ground truth from noisy and unreliable data. To do so, existing approaches rely on collecting redundant information from the crowd, and aggregating it with some probabilistic method. However, oftentimes such methods are computationally inefficient, are restricted to some specific settings, or lack theoretical guarantees. In this paper, we revisit the problem of binary classification from crowdsourced data. Specifically we propose Streaming Bayesian Inference for Crowdsourcing (SBIC), a new algorithm that does not suffer from any of these limitations. First, SBIC has low complexity and can be used in a real-time online setting. Second, SBIC has the same accuracy as the best state-of-the-art algorithms in all settings. Third, SBIC has provable asymptotic guarantees both in the online and offline settings.

Saaduddin Mahmud, Moumita Choudhury, Md. Mosaddek Khan et al.

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. However, the potential of this metaheuristic has not been utilized in Distributed Constraint Optimization Problems (DCOPs), a well-known class of combinatorial optimization problems prevalent in Multi-Agent Systems. In this paper, we present a novel population-based algorithm, Anytime Evolutionary DCOP (AED), that uses evolutionary optimization to solve DCOPs. In AED, the agents cooperatively construct an initial set of random solutions and gradually improve them through a new mechanism that considers an optimistic approximation of local benefits. Moreover, we present a new anytime update mechanism for AED that identifies the best among a distributed set of candidate solutions and notifies all the agents when a new best is found. In our theoretical analysis, we prove that AED is anytime. Finally, we present empirical results indicating AED outperforms the state-of-the-art DCOP algorithms in terms of solution quality.

Jiarui Gan, Qingyu Guo, Long Tran-Thanh et al.

In Stackelberg security games when information about the attacker's payoffs is uncertain, algorithms have been proposed to learn the optimal defender commitment by interacting with the attacker and observing their best responses. In this paper, we show that, however, these algorithms can be easily manipulated if the attacker responds untruthfully. As a key finding, attacker manipulation normally leads to the defender learning a maximin strategy, which effectively renders the learning attempt meaningless as to compute a maximin strategy requires no additional information about the other player at all. 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. We provide a polynomial-time algorithm to compute the optimal such policy, and in addition, a heuristic approach that applies even when the attacker's payoff space is infinite or completely unknown. Empirical evaluation shows that our approaches can improve the defender's utility significantly as compared to the situation when attacker manipulation is ignored.

Dong Quan Vu, Patrick Loiseau, Alonso Silva et al.

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. Indeed, due to their extremely large strategy space, it remains an open question how one can efficiently learn in these games. In this work, we show that the online CB and HS games can be cast as path planning problems with side-observations (SOPPP): at each stage, a learner chooses a path on a directed acyclic graph and suffers the sum of losses that are adversarially assigned to the corresponding edges; and she then receives semi-bandit feedback with side-observations (i.e., she observes the losses on the chosen edges plus some others). We propose a novel algorithm, EXP3-OE, the first-of-its-kind with guaranteed efficient running time for SOPPP without requiring any auxiliary oracle. We provide an expected-regret bound of EXP3-OE in SOPPP matching the order of the best benchmark in the literature. Moreover, we introduce additional assumptions on the observability model under which we can further improve the regret bounds of EXP3-OE. We illustrate the benefit of using EXP3-OE in SOPPP by applying it to the online CB and HS games.

Tin Leelavimolsilp, Long Tran-Thanh, Sebastian Stein et al.

Proof-of-Work blockchain, despite its numerous benefits, is still not an entirely secure technology due to the existence of Selfish Mining (SM) strategies that can disrupt the system and its mining economy. While the effect of SM has been studied mostly in a two-miners scenario, it has not been investigated in a more practical context where there are multiple malicious miners individually performing SM. To fill this gap, we carry out an empirical study that separately accounts for different numbers of SM miners (who always perform SM) and strategic miners (who choose either SM or Nakamoto's mining protocol depending on which maximises their individual mining reward). Our result shows that SM is generally more effective as the number of SM miners increases, however its effectiveness does not vary in the presence of a large number of strategic miners. Under specific mining power distributions, we also demonstrate that multiple miners can perform SM and simultaneously gain higher mining rewards than they should. Surprisingly, we also show that the more strategic miners there are, the more robust the systems become. Since blockchain miners should naturally be seen as self-interested strategic miners, our findings encourage blockchain system developers and engineers to attract as many miners as possible to prevent SM and similar behaviour.

Anshuka Rangi, Massimo Franceschetti, Long Tran-Thanh

This paper investigates the adversarial Bandits with Knapsack (BwK) online learning problem, where a player repeatedly chooses to perform an action, pays the corresponding cost, and receives a reward associated with the action. The player is constrained by the maximum budget $B$ that can be spent to perform actions, and the rewards and the costs of the actions are assigned by an adversary. This problem has only been studied in the restricted setting where the reward of an action is greater than the cost of the action, while we provide a solution in the general setting. Namely, we propose EXP3.BwK, a novel algorithm that achieves order optimal regret. We also propose EXP3++.BwK, which is order optimal in the adversarial BwK setup, and incurs an almost optimal expected regret with an additional factor of $\log(B)$ in the stochastic BwK setup. Finally, we investigate the case of having large costs for the actions (i.e., they are comparable to the budget size $B$), and show that for the adversarial setting, achievable regret bounds can be significantly worse, compared to the case of having costs bounded by a constant, which is a common assumption within the BwK literature.

Zheyuan Ryan Shi, Ziye Tang, Long Tran-Thanh et al.

Effective game-theoretic modeling of defender-attacker behavior is becoming increasingly important. In many domains, the defender functions not only as a player but also the designer of the game's payoff structure. 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. Focusing on problems with weighted L^1-norm form constraint, we present (i) a mixed integer linear program-based algorithm with approximation guarantee; (ii) a branch-and-bound based algorithm with improved efficiency achieved by effective pruning; (iii) a polynomial time approximation scheme for a special but practical class of problems. In addition, we show that problems under budget constraints in L^0-norm form and weighted L^\infty-norm form can be solved in polynomial time. We provide an extensive experimental evaluation of our proposed algorithms.

Tin Leelavimolsilp, Long Tran-Thanh, Sebastian Stein

Eyal and Sirer's selfish mining strategy has demonstrated that Bitcoin system is not secure even if 50% of total mining power is held by altruistic miners. Since then, researchers have been investigating either to improve the efficiency of selfish mining, or how to defend against it, typically in a single selfish miner setting. Yet there is no research on a selfish mining strategies concurrently used by multiple miners in the system. The effectiveness of such selfish mining strategies and their required mining power under such multiple selfish miners setting remains unknown. In this paper, a preliminary investigation and our findings of selfish mining strategy used by multiple miners are reported. In addition, the conventional model of Bitcoin system is slightly redesigned to tackle its shortcoming: namely, a concurrency of individual mining processes. Although a theoretical analysis of selfish mining strategy under this setting is yet to be established, the current findings based on simulations is promising and of great interest. In particular, our work shows that a lower bound of power threshold required for selfish mining strategy decreases in proportion to a number of selfish miners. Moreover, there exist Nash equilibria where all selfish miners in the system do not change to an honest mining strategy and simultaneously earn their unfair amount of mining reward given that they equally possess sufficiently large mining power. Lastly, our new model yields a power threshold for mounting selfish mining strategy slightly greater than one from the conventional model.

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. However, we still lack a theoretical understanding of how to collect the labels from the crowd in an optimal way. In this paper we focus on the problem of worker allocation and compare two active learning policies proposed in the empirical literature with a uniform allocation of the available budget. To this end we make a thorough mathematical analysis of the problem and derive a new bound on the performance of the system. Furthermore we run extensive simulations in a more realistic scenario and show that our theoretical results hold in practice.

Nhat V. Q. Truong, Sebastian Stein, Long Tran-Thanh et al.

Significant effort has been made to understand user motivation and to elicit user participation in crowdsourcing systems. However, incentive engineering, i.e., designing incentives that can purposefully motivate users, is still an open question and remains one of the key challenges of crowdsourcing initiatives. In this work in progress, we propose a general and systematic incentive engineering framework that system designers can use to implement appropriate incentives in order to effect desirable user behaviours.

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. These problems arise in many settings such as maximum entropy methods in natural language processing, and risk-averse decision-making, but current best-arm identification techniques fail in these domains. We propose a new approach, that combines functional estimation and arm elimination, to tackle this problem. This method achieves provably efficient performance guarantees. In addition, we illustrate this method on a number of important functionals in risk management and information theory, and refine our generic theoretical results in those cases.

Long Tran-Thanh, Archie Chapman, Alex Rogers et al.

In budget-limited multi-armed bandit (MAB) problems, the learner's actions are costly and constrained by a fixed budget. Consequently, an optimal exploitation policy may not be to pull the optimal arm repeatedly, as is the case in other variants of MAB, but rather to pull the sequence of different arms that maximises the agent's total reward within the budget. This difference from existing MABs means that new approaches to maximising the total reward are required. Given this, we develop two pulling policies, namely: (i) KUBE; and (ii) fractional KUBE. Whereas the former provides better performance up to 40% in our experimental settings, the latter is computationally less expensive. We also prove logarithmic upper bounds for the regret of both policies, and show that these bounds are asymptotically optimal (i.e. they only differ from the best possible regret by a constant factor).