arXiv subjects

Bogdan Cautis

Publications and source records attributed to Bogdan Cautis.

15 recordsLinked to original sources

arXiv2026

Structural Adversarial Attacks on Relational Deep Learning under Integrity Constraints

Relational Deep Learning (RDL) has become a standard methodology for machine learning on relational databases: the database is encoded as a heterogeneous temporal graph in which tuples become nodes and primary-key to foreign-key (PK-FK) dependencies become typed edges, over which a graph neural network is trained for downstream prediction. We study the adversarial robustness of this pipeline. We consider a white-box attacker who knows how the graph is built and the model is trained, reasons about perturbations on the graph, but can only act on the upstream database, by rewiring foreign-key references while preserving the integrity constraints of the schema (foreign-key validity, the degree-one FK constraint, and functional dependencies). This restricts the attacker to a constrained, combinatorial set of admissible edits under a global perturbation budget, which is intractable to explore exhaustively and made non-additive by GNN message passing. We investigate seven attack heuristics - two random sampling baselines and five gradient-guided variants that exploit differentiable edge masks - and evaluate them on the RelBench rel-f1 benchmark. Gradient-based attacks consistently outperform random baselines on regression tasks, whereas gains on classification are smaller, which we attribute to low label-flip rates and greater local stability of classification outputs.

cs.LG↗

arXiv2024

Hyperparametric Robust and Dynamic Influence Maximization

We study the problem of robust influence maximization in dynamic diffusion networks. In line with recent works, we consider the scenario where the network can undergo insertion and removal of nodes and edges, in discrete time steps, and the influence weights are determined by the features of the corresponding nodes and a global hyperparameter. Given this, our goal is to find, at every time step, the seed set maximizing the worst-case influence spread across all possible values of the hyperparameter. We propose an approximate solution using multiplicative weight updates and a greedy algorithm, with provable quality guarantees. Our experiments validate the effectiveness and efficiency of the proposed methods.

cs.DB↗

arXiv2024

Influence Maximization via Graph Neural Bandits

We consider a ubiquitous scenario in the study of Influence Maximization (IM), in which there is limited knowledge about the topology of the diffusion network. We set the IM problem in a multi-round diffusion campaign, aiming to maximize the number of distinct users that are influenced. Leveraging the capability of bandit algorithms to effectively balance the objectives of exploration and exploitation, as well as the expressivity of neural networks, our study explores the application of neural bandit algorithms to the IM problem. We propose the framework IM-GNB (Influence Maximization with Graph Neural Bandits), where we provide an estimate of the users' probabilities of being influenced by influencers (also known as diffusion seeds). This initial estimate forms the basis for constructing both an exploitation graph and an exploration one. Subsequently, IM-GNB handles the exploration-exploitation tradeoff, by selecting seed nodes in real-time using Graph Convolutional Networks (GCN), in which the pre-estimated graphs are employed to refine the influencers' estimated rewards in each contextual setting. Through extensive experiments on two large real-world datasets, we demonstrate the effectiveness of IM-GNB compared with other baseline methods, significantly improving the spread outcome of such diffusion campaigns, when the underlying network is unknown.

cs.LG↗

arXiv2024

Predicting Cascading Failures with a Hyperparametric Diffusion Model

In this paper, we study cascading failures in power grids through the lens of information diffusion models. Similar to the spread of rumors or influence in an online social network, it has been observed that failures (outages) in a power grid can spread contagiously, driven by viral spread mechanisms. We employ a stochastic diffusion model that is Markovian (memoryless) and local (the activation of one node, i.e., transmission line, can only be caused by its neighbors). Our model integrates viral diffusion principles with physics-based concepts, by correlating the diffusion weights (contagion probabilities between transmission lines) with the hyperparametric Information Cascades (IC) model. We show that this diffusion model can be learned from traces of cascading failures, enabling accurate modeling and prediction of failure propagation. This approach facilitates actionable information through well-understood and efficient graph analysis methods and graph diffusion simulations. Furthermore, by leveraging the hyperparametric model, we can predict diffusion and mitigate the risks of cascading failures even in unseen grid configurations, whereas existing methods falter due to a lack of training data. Extensive experiments based on a benchmark power grid and simulations therein show that our approach effectively captures the failure diffusion phenomena and guides decisions to strengthen the grid, reducing the risk of large-scale cascading failures. Additionally, we characterize our model's sample complexity, improving upon the existing bound.

cs.SI↗

arXiv2024

Scalable Continuous-time Diffusion Framework for Network Inference and Influence Estimation

The study of continuous-time information diffusion has been an important area of research for many applications in recent years. When only the diffusion traces (cascades) are accessible, cascade-based network inference and influence estimation are two essential problems to explore. Alas, existing methods exhibit limited capability to infer and process networks with more than a few thousand nodes, suffering from scalability issues. In this paper, we view the diffusion process as a continuous-time dynamical system, based on which we establish a continuous-time diffusion model. Subsequently, we instantiate the model to a scalable and effective framework (FIM) to approximate the diffusion propagation from available cascades, thereby inferring the underlying network structure. Furthermore, we undertake an analysis of the approximation error of FIM for network inference. To achieve the desired scalability for influence estimation, we devise an advanced sampling technique and significantly boost the efficiency. We also quantify the effect of the approximation error on influence estimation theoretically. Experimental results showcase the effectiveness and superior scalability of FIM on network inference and influence estimation.

cs.SI↗

arXiv2023

Influence Maximization with Fairness at Scale (Extended Version)

In this paper, we revisit the problem of influence maximization with fairness, which aims to select k influential nodes to maximise the spread of information in a network, while ensuring that selected sensitive user attributes are fairly affected, i.e., are proportionally similar between the original network and the affected users. Recent studies on this problem focused only on extremely small networks, hence the challenge remains on how to achieve a scalable solution, applicable to networks with millions or billions of nodes. We propose an approach that is based on learning node representations for fair spread from diffusion cascades, instead of the social connectivity s.t. we can deal with very large graphs. We propose two data-driven approaches: (a) fairness-based participant sampling (FPS), and (b) fairness as context (FAC). Spread related user features, such as the probability of diffusing information to others, are derived from the historical information cascades, using a deep neural network. The extracted features are then used in selecting influencers that maximize the influence spread, while being also fair with respect to the chosen sensitive attributes. In FPS, fairness and cascade length information are considered independently in the decision-making process, while FAC considers these information facets jointly and considers correlations between them. The proposed algorithms are generic and represent the first policy-driven solutions that can be applied to arbitrary sets of sensitive attributes at scale. We evaluate the performance of our solutions on a real-world public dataset (Sina Weibo) and on a hybrid real-synthethic dataset (Digg), which exhibit all the facets that we exploit, namely diffusion network, diffusion traces, and user profiles. These experiments show that our methods outperform the state-the-art solutions in terms of spread, fairness, and scalability.

cs.SI↗

arXiv2022

IGNiteR: News Recommendation in Microblogging Applications (Extended Version)

News recommendation is one of the most challenging tasks in recommender systems, mainly due to the ephemeral relevance of news to users. As social media, and particularly microblogging applications like Twitter or Weibo, gains popularity as platforms for news dissemination, personalized news recommendation in this context becomes a significant challenge. We revisit news recommendation in the microblogging scenario, by taking into consideration social interactions and observations tracing how the information that is up for recommendation spreads in an underlying network. We propose a deep-learning based approach that is diffusion and influence-aware, called Influence-Graph News Recommender (IGNiteR). It is a content-based deep recommendation model that jointly exploits all the data facets that may impact adoption decisions, namely semantics, diffusion-related features pertaining to local and global influence among users, temporal attractiveness, and timeliness, as well as dynamic user preferences. To represent the news, a multi-level attention-based encoder is used to reveal the different interests of users. This news encoder relies on a CNN for the news content and on an attentive LSTM for the diffusion traces. For the latter, by exploiting previously observed news diffusions (cascades) in the microblogging medium, users are mapped to a latent space that captures potential influence on others or susceptibility of being influenced for news adoptions. Similarly, a time-sensitive user encoder enables us to capture the dynamic preferences of users with an attention-based bidirectional LSTM. We perform extensive experiments on two real-world datasets, showing that IGNiteR outperforms the state-of-the-art deep-learning based news recommendation methods.

cs.IR↗

arXiv2022

Contextual Bandits for Advertising Campaigns: A Diffusion-Model Independent Approach (Extended Version)

Motivated by scenarios of information diffusion and advertising in social media, we study an influence maximization problem in which little is assumed to be known about the diffusion network or about the model that determines how information may propagate. In such a highly uncertain environment, one can focus on multi-round diffusion campaigns, with the objective to maximize the number of distinct users that are influenced or activated, starting from a known base of few influential nodes. During a campaign, spread seeds are selected sequentially at consecutive rounds, and feedback is collected in the form of the activated nodes at each round. A round's impact (reward) is then quantified as the number of newly activated nodes. Overall, one must maximize the campaign's total spread, as the sum of rounds' rewards. In this setting, an explore-exploit approach could be used to learn the key underlying diffusion parameters, while running the campaign. We describe and compare two methods of contextual multi-armed bandits, with upper-confidence bounds on the remaining potential of influencers, one using a generalized linear model and the Good-Turing estimator for remaining potential (GLM-GT-UCB), and another one that directly adapts the LinUCB algorithm to our setting (LogNorm-LinUCB). We show that they outperform baseline methods using state-of-the-art ideas, on synthetic and real-world data, while at the same time exhibiting different and complementary behavior, depending on the scenarios in which they are deployed.

cs.LG↗

arXiv2021

HADAD: A Lightweight Approach for Optimizing Hybrid Complex Analytics Queries (Extended Version)

Hybrid complex analytics workloads typically include (i) data management tasks (joins, selections, etc. ), easily expressed using relational algebra (RA)-based languages, and (ii) complex analytics tasks (regressions, matrix decompositions, etc.), mostly expressed in linear algebra (LA) expressions. Such workloads are common in many application areas, including scientific computing, web analytics, and business recommendation. Existing solutions for evaluating hybrid analytical tasks - ranging from LA-oriented systems, to relational systems (extended to handle LA operations), to hybrid systems - either optimize data management and complex tasks separately, exploit RA properties only while leaving LA-specific optimization opportunities unexploited, or focus heavily on physical optimization, leaving semantic query optimization opportunities unexplored. Additionally, they are not able to exploit precomputed (materialized) results to avoid recomputing (part of) a given mixed (RA and/or LA) computation. In this paper, we take a major step towards filling this gap by proposing HADAD, an extensible lightweight approach for optimizing hybrid complex analytics queries, based on a common abstraction that facilitates unified reasoning: a relational model endowed with integrity constraints. Our solution can be naturally and portably applied on top of pure LA and hybrid RA-LA platforms without modifying their internals. An extensive empirical evaluation shows that HADAD yields significant performance gains on diverse workloads, ranging from LA-centered to hybrid.

cs.DB↗

arXiv2020

Bandits Under The Influence (Extended Version)

Recommender systems should adapt to user interests as the latter evolve. A prevalent cause for the evolution of user interests is the influence of their social circle. In general, when the interests are not known, online algorithms that explore the recommendation space while also exploiting observed preferences are preferable. We present online recommendation algorithms rooted in the linear multi-armed bandit literature. Our bandit algorithms are tailored precisely to recommendation scenarios where user interests evolve under social influence. In particular, we show that our adaptations of the classic LinREL and Thompson Sampling algorithms maintain the same asymptotic regret bounds as in the non-social case. We validate our approach experimentally using both synthetic and real datasets.

cs.LG↗

arXiv2017

Algorithms for Online Influencer Marketing

Influence maximization is the problem of finding influential users, or nodes, in a graph so as to maximize the spread of information. It has many applications in advertising and marketing on social networks. In this paper, we study a highly generic version of influence maximization, one of optimizing influence campaigns by sequentially selecting "spread seeds" from a set of influencers, a small subset of the node population, under the hypothesis that, in a given campaign, previously activated nodes remain "persistently" active throughout and thus do not yield further rewards. This problem is in particular relevant for an important form of online marketing, known as influencer marketing, in which the marketers target a sub-population of influential people, instead of the entire base of potential buyers. Importantly, we make no assumptions on the underlying diffusion model and we work in a setting where neither a diffusion network nor historical activation data are available. We call this problem online influencer marketing with persistence (in short, OIMP). We first discuss motivating scenarios and present our general approach. We introduce an estimator on the influencers' remaining potential -- the expected number of nodes that can still be reached from a given influencer -- and justify its strength to rapidly estimate the desired value, relying on real data gathered from Twitter. We then describe a novel algorithm, GT-UCB, relying on upper confidence bounds on the remaining potential. We show that our approach leads to high-quality spreads on both simulated and real datasets, even though it makes almost no assumptions on the diffusion medium. Importantly, it is orders of magnitude faster than state-of-the-art influence maximization methods, making it possible to deal with large-scale online scenarios.

cs.SI↗

arXiv2015

A Network-Aware Approach for Searching As-You-Type in Social Media (Extended Version)

We present in this paper a novel approach for as-you-type top-$k$ keyword search over social media. We adopt a natural "network-aware" interpretation for information relevance, by which information produced by users who are closer to the seeker is considered more relevant. In practice, this query model poses new challenges for effectiveness and efficiency in online search, even when a complete query is given as input in one keystroke. This is mainly because it requires a joint exploration of the social space and classic IR indexes such as inverted lists. We describe a memory-efficient and incremental prefix-based retrieval algorithm, which also exhibits an anytime behavior, allowing to output the most likely answer within any chosen running-time limit. We evaluate it through extensive experiments for several applications and search scenarios, including searching for posts in micro-blogging (Twitter and Tumblr), as well as searching for businesses based on reviews in Yelp. They show that our solution is effective in answering real-time as-you-type searches over social media.

cs.IR↗

arXiv2013

Rewriting XPath Queries using View Intersections: Tractability versus Completeness

The standard approach for optimization of XPath queries by rewriting using views techniques consists in navigating inside a view's output, thus allowing the usage of only one view in the rewritten query. Algorithms for richer classes of XPath rewritings, using intersection or joins on node identifiers, have been proposed, but they either lack completeness guarantees, or require additional information about the data. We identify the tightest restrictions under which an XPath can be rewritten in polynomial time using an intersection of views and propose an algorithm that works for any documents or type of identifiers. As a side-effect, we analyze the complexity of the related problem of deciding if an XPath with intersection can be equivalently rewritten as one without intersection or union. We extend our formal study of the view-based rewriting problem for XPath by describing also (i) algorithms for more complex rewrite plans, with no limitations on the number of intersection and navigation steps inside view outputs they employ, and (ii) adaptations of our techniques to deal with XML documents without persistent node Ids, in the presence of XML keys. Complementing our computational complexity study, we describe a proof-of-concept implementation of our techniques and possible choices that may speed up execution in practice, regarding how rewrite plans are built, tested and executed. We also give a thorough experimental evaluation of these techniques, focusing on scalability and the running time improvements achieved by the execution of view-based plans.

cs.DB↗

arXiv2012

Efficient Top-K Retrieval in Online Social Tagging Networks

We consider in this paper top-k query answering in social tagging systems, also known as folksonomies. This problem requires a significant departure from existing, socially agnostic techniques. In a network-aware context, one can (and should) exploit the social links, which can indicate how users relate to the seeker and how much weight their tagging actions should have in the result build-up. We propose an algorithm that has the potential to scale to current applications. While the problem has already been considered in previous literature, this was done either under strong simplifying assumptions or under choices that cannot scale to even moderate-size real world applications. We first consider a key aspect of the problem, which is accessing the closest or most relevant users for a given seeker. We describe how this can be done on the fly (without any pre-computations) for several possible choices - arguably the most natural ones - of proximity computation in a user network. Based on this, our top-k algorithm is sound and complete, while addressing the scalability issues of the existing ones. Importantly, our technique is instance optimal in the case when the search relies exclusively on the social weight of tagging actions. To further reduce response times, we then consider directions for efficiency by approximation. Extensive experiments on real world data show that our techniques can drastically improve the response time, without sacrificing precision.

cs.IR↗

arXiv2012

Answering Queries using Views over Probabilistic XML: Complexity and Tractability

We study the complexity of query answering using views in a probabilistic XML setting, identifying large classes of XPath queries -- with child and descendant navigation and predicates -- for which there are efficient (PTime) algorithms. We consider this problem under the two possible semantics for XML query results: with persistent node identifiers and in their absence. Accordingly, we consider rewritings that can exploit a single view, by means of compensation, and rewritings that can use multiple views, by means of intersection. Since in a probabilistic setting queries return answers with probabilities, the problem of rewriting goes beyond the classic one of retrieving XML answers from views. For both semantics of XML queries, we show that, even when XML answers can be retrieved from views, their probabilities may not be computable. For rewritings that use only compensation, we describe a PTime decision procedure, based on easily verifiable criteria that distinguish between the feasible cases -- when probabilistic XML results are computable -- and the unfeasible ones. For rewritings that can use multiple views, with compensation and intersection, we identify the most permissive conditions that make probabilistic rewriting feasible, and we describe an algorithm that is sound in general, and becomes complete under fairly permissive restrictions, running in PTime modulo worst-case exponential time equivalence tests. This is the best we can hope for since intersection makes query equivalence intractable already over deterministic data. Our algorithm runs in PTime whenever deterministic rewritings can be found in PTime.

cs.DB↗