Research Topics

Algorithmic Fairness

Fairness of Recourse

We propose novel fairness definitions concerning algorithmic recourse. For an individual that receives an undesirable outcome (e.g., loan application rejected), recourse is a way to reverse the outcome (e.g., increase down payment). Recourse incurs a cost for the individual that can be measured quantitatively. Our definitions investigate whether subpopulations have comparable costs, i.e., bear the same burden, for recourse. We have developed a method, termed FACTS, to audit a model for fairness, i.e., find subgroups where unfairness exists.

A discovered subgroup where unfairness of recourse exists.

Our approach is integrated within the IBM AIF 360 tool. See a demo notebook here.


(2023). Fairness Aware Counterfactuals for Subgroups. NeurIPS 2023 - 37th Conference on Neural Information Processing Systems.

PDF Cite Code DOI arXiv URL Rank A*

Spatial Fairness

In many cases, it is important to ensure that a model does not discriminate against individuals on the basis of their location (place of origin, home address, etc.). We consider location as the protected attribute and we want the algorithm to exhibit spatial fairness For example, consider a model that predicts whether mortgage loan applications are accepted. Its decisions should not discriminate based on the home address of the applicant. This could be to avoid redlining, i.e., indirectly discriminating based on ethnicity/race due to strong correlations between the home address and certain ethnic/racial groups, or to avoid gentrification, e.g., when applications in a poor urban area are systematically rejected to attract wealthier people. We have developed a method to audit a model for spatial fairness, i.e., find areas where spatial unfairness exists.

Discovered areas in the USA where spatial unfairness exists for mortgage loan applications.


(2023). Auditing for Spatial Fairness. Proceedings 26th International Conference on Extending Database Technology, EDBT 2023, Ioannina, Greece, March 28-31, 2023.

PDF Cite Code Slides DOI arXiv URL Rank A

Fairness in Recommender Systems

In recommender systems, fairness may concern either the consumers (end users, buyers, etc.) that receive recommendations, or the providers (producers, sellers, etc.) of the items being recommended. We have developed a common method that post-processes recommendations so as to ensure either consumer or provider fairness.

When recommendations concern a group of people, rather than an invidivual, the system must also consider fairness within the group. That means each member of the group should receive roughly the same utility from the recommendations.


(2019). A Common Approach for Consumer and Provider Fairness in Recommendations. ACM Conference on Recommender Systems (RecSys), Late-Breaking Results.

PDF Cite Rank A

(2019). Top-N group recommendations with fairness. ACM/SIGAPP Symposium on Applied Computing (SAC).


Model Explainability

Global Counterfactual Explainability

We propose a method for global explainability of black box models using counterfactual explanations. A counterfactual explanation locally explains an outcome by providing the minimal changes necessary to reverse the outcome, e.g., “if you had five more years of experience, your job application would have been accepted”. We develop a method, termed GLANCE, that summarizes all counterfactual explanations for a given model.

Three actions that summarize all counterfactual explanations.


(2024). GLANCE - Global Actions in a Nutshell for Counterfactual Explainability. Under Review.

PDF Code

Example-Based Explanations

For many use-cases, it is often important to explain the prediction of a black-box model by identifying the most influential training data samples. We propose AIDE, Antithetical, Intent-based, and Diverse Example-Based Explanations, an approach for providing antithetical (i.e., contrastive), intent-based, diverse explanations for opaque and complex models. AIDE distinguishes three types of explainability intents: interpreting a correct, investigating a wrong, and clarifying an ambiguous prediction. For each intent, AIDE selects an appropriate set of influential training samples that support or oppose the prediction either directly or by contrast. To provide a succinct summary, AIDE uses diversity-aware sampling to avoid redundancy and increase coverage of the training data.

To explain an ambiguous prediction, AIDE provides influential training samples that support and oppose it.


(2024). AIDE - Antithetical, Intent-based, and Diverse Example-Based Explanations. Under Review.


Counterfactual Explanations for Recommendations

We develop a post-hoc, model-agnostic explanation mechanism for recommender systems. It returns counterfactual explanations defined as those minimal changes to the user’s interaction history that would result in the system not making the recommendation that is to be explained. Because counterfactuals achieve the desired output on the recommender itself, rather than a proxy, our explanation mechanism has the same fidelity as model-specific post-hoc explanations. Moreover, it is completely private, since no other information besides the user’s interaction history is required to extract counterfactuals. Finally, owing to their simplicity, counterfactuals are scrutable, as they present specific interactions from the user’s history, and potentially actionable.

Counterfactual explanations for recommender systems.


(2021). Model-Agnostic Counterfactual Explanations of Recommendations. Proceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization, UMAP 2021, Utrecht, The Netherlands, June, 21-25, 2021.

PDF Cite Code Slides Video DOI URL

Text Mining

Entity Extraction using Structured Data

We propose THOR a novel method to extract information from text, that unlike related approaches, neither relies on complex rules nor models trained with large annotated corpus. Instead, THOR is lightweight and exploits integrated data and its schema without the need for human annotations. THOR significantly outperforms state-of-the-art Large Language Models in text conceptualization, particularly in entity recognition tasks, for data integration settings.

An example where THOR conceptualizes text based on available structured data.


(2024). Mitigating Data Sparsity in Integrated Data through Text Conceptualization. ICDE 2024 - 40th International Conference on Extending Database Technology.

PDF Cite Code Rank A*

Record Linkage for Complex Records

We propose TokenJoin, a method for linking complex records, i.e., identifying similar pairs among a collection of complex records. A complex record is a set of simpler text entities, such as a set of addresses. To increase robustness, our approach is based on a relaxed match criterion, the fuzzy set similarity join, which calculates the similarity of two complex records based on maximum weighted bipartite matching instead of overlap.

TokenJoin is able to match records where exact matching would fail.


(2022). TokenJoin: Efficient Filtering for Set Similarity Join with Maximum Weighted Bipartite Matching. Proc. VLDB Endow..

PDF Cite Code DOI Rank A*

Data Intensive Pipelines

Optimizing Machine Learning Pipelines

We propose HYPPO, a novel system to optimize pipelines encountered in exploratory machine learning. HYPPO exploits alternative computational paths of artifacts from past executions to derive better execution plans while reusing materialized artifacts. Adding alternative computations introduces new challenges for exploratory machine learning regarding workload representation, system architecture, and optimal execution plan generation. To this end, we present a novel workload representation based on directed hypergraphs, and we formulate the problem of discovering the optimal execution plan as a search problem over directed hypergraphs and that of selecting artifacts to materialize as an optimization problem.

Overview of the pipeline optimization process in HYPPO.


(2024). HYPPO - Using Equivalences to Optimize Pipelines in Exploratory Machine Learning. ICDE 2024 - 40th International Conference on Extending Database Technology.

PDF Cite Code Rank A*

Summarizing Streaming Big Data

When analyzing big data, it is often necessary to work with data synopses, approximate summaries of the data that come with guarantees. We propose a novel synopsis-as-a-service paradigm and design a Synopses Data Engine as a Service (SDEaaS) system, built on top of Apache Flink, that combines the virtues of parallel processing and stream summarization towards delivering interactive analytics at extreme scale.

Architecture of the Synopses Data Engine as a Service.


(2023). And synopses for all: A synopses data engine for extreme scale analytics-as-a-service. Inf. Syst..