Learning Unknown Graphs

Cesa-Bianchi, Nicolò; Gentile, Claudio; Vitale, Fabio

doi:10.1007/978-3-642-04414-4_13

Cited by 7 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other variants consider settings in which the number of copies of the item to sell is limited [1,5,6], buyers act strategically in order to maximize their utility in future rounds [2,28,37,29], or there are features associated with the goods on sale [21]. In the stochastic setting, previous works typically assume parametric [12], locally smooth [32], or piecewise constant demand curves [15,27].…”

Section: Further Related Workmentioning

confidence: 99%

Bilateral Trade: A Regret Minimization Perspective

et al. 2024

View full text Add to dashboard Cite

Bilateral trade, a fundamental topic in economics, models the problem of intermediating between two strategic agents, a seller and a buyer, willing to trade a good for which they hold private valuations. In this paper, we cast the bilateral trade problem in a regret minimization framework over T rounds of seller/buyer interactions, with no prior knowledge on their private valuations. Our main contribution is a complete characterization of the regret regimes for fixed-price mechanisms with different feedback models and private valuations, using as a benchmark the best fixed price in hindsight. More precisely, we prove the following tight bounds on the regret: [Formula: see text] for full-feedback (i.e., direct revelation mechanisms). [Formula: see text] for realistic feedback (i.e., posted-price mechanisms) and independent seller/buyer valuations with bounded densities. [Formula: see text] for realistic feedback and seller/buyer valuations with bounded densities. [Formula: see text] for realistic feedback and independent seller/buyer valuations. [Formula: see text] for the adversarial setting. Funding: This work was partially supported by the European Research Council Advanced [Grant 788893] AMDROMA “Algorithmic and Mechanism Design Research in Online Markets”, the Ministero dell’Istruzione, dell’Università e della Ricerca PRIN project ALGADIMAR “Algorithms, Games, and Digital Markets”, the AI Interdisciplinary Institute ANITI (funded by the French “Investing for the Future—PIA3” program under the [Grant agreement ANR-19-PI3A-0004], the project BOLD from the French national research agency (ANR), the EU Horizon 2020 ICT-48 research and innovation action ELISE (European Learning and Intelligent Systems Excellence, [Grant agreement 951847].

show abstract

Section: Further Related Workmentioning

confidence: 99%

Bilateral Trade: A Regret Minimization Perspective

et al. 2024

View full text Add to dashboard Cite

show abstract

“…Work on active learning for graph-based problems has focused on node and graph classification, as well as on various tasks at the link level [14,23]. The graph classification task considers data samples as graph objects, useful, e.g., for drug discovery and subgraph mining [24], while the node classification aims to label nodes in graphs [25][26][27][28]. Active learning has also been used for predicting the sign (positive or negative) of edges in signed networks, where some of the edge labels are queried [6].…”

Section: Related Workmentioning

confidence: 99%

ALPINE: Active Link Prediction Using Network Embedding

et al. 2021

View full text Add to dashboard Cite

Many real-world problems can be formalized as predicting links in a partially observed network. Examples include Facebook friendship suggestions, the prediction of protein–protein interactions, and the identification of hidden relationships in a crime network. Several link prediction algorithms, notably those recently introduced using network embedding, are capable of doing this by just relying on the observed part of the network. Often, whether two nodes are linked can be queried, albeit at a substantial cost (e.g., by questionnaires, wet lab experiments, or undercover work). Such additional information can improve the link prediction accuracy, but owing to the cost, the queries must be made with due consideration. Thus, we argue that an active learning approach is of great potential interest and developed ALPINE (Active Link Prediction usIng Network Embedding), a framework that identifies the most useful link status by estimating the improvement in link prediction accuracy to be gained by querying it. We proposed several query strategies for use in combination with ALPINE, inspired by the optimal experimental design and active learning literature. Experimental results on real data not only showed that ALPINE was scalable and boosted link prediction accuracy with far fewer queries, but also shed light on the relative merits of the strategies, providing actionable guidance for practitioners.

show abstract

“…Further, as an extension of this application area, correlation clustering can be used to predict the sign of the missing edge, that is, as a link classification problem tool. It works in a supervised transductive framework to give formal interpretations to prediction complexity of link classification (Cesa‐Bianchi, Gentile, Vitale, & Zappella, ). In the broader areas of machine learning and data mining, the problems of aggregating multiple clusterings and the problem of consensus clustering can be viewed as special cases of correlation clustering.…”

Section: Real‐time Applications and General Uses Of Correlation Clustmentioning

confidence: 99%

Correlation clustering methodologies and their fundamental results

2017

View full text Add to dashboard Cite

Correlation clustering possibly represents the most intuitive form of clustering construction. It gives solutions that can be approximated while automatically selecting the number of clusters. This approach handles scenarios where the focus is on relationships between the objects instead of on actual representations of the objects. The suitability of this method extends to the structured objects, for which feature vectors are not easy to obtain. Given the increasing scale of data these days, correlation clustering has become a powerful addition to the fields of data mining and agnostic learning. Correlation clustering considers a weighted graph G=(V,E), where the edge weight indicates whether two nodes are similar (positive edge weight) or different (negative edge weight). The task is to find a clustering that either maximizes agreements or minimizes disagreements. Unlike other clustering algorithms, this does not require choosing the number of clusters (k) in advance. The objective to minimize the sum of weights of the cut edges is independent of the number of clusters. Methodologies, such as approximations and linear programming formulations, have been used to approach this problem. This paper focuses on the problem of correlation clustering and lists the solutions proposed by various researchers. These solutions approach the problem using different computational techniques. Correlation clustering‐based applications such as entity de‐duplication, signed social networks, and problem of aggregating multiples have also been discussed.

show abstract

Learning Unknown Graphs

Cited by 7 publications

References 11 publications

Bilateral Trade: A Regret Minimization Perspective

Bilateral Trade: A Regret Minimization Perspective

ALPINE: Active Link Prediction Using Network Embedding

Correlation clustering methodologies and their fundamental results

Contact Info

Product

Resources

About