Doctoral Consortium Track

Participatory budgeting (PB) is an implementation of direct democracy that allows members of a community to make collective budgeting decisions. However, existing PB processes rely upon a pre-defined central budget. We introduce a framework for pooling resources in addition to selecting projects, which we call PB with Resource Pooling. We motivate the key characteristics of this model and the basic properties we would like a mechanism to satisfy. We summarize results and discuss interesting questions related to our framework.

My research focuses on using algorithmic systems alongside human collaborators to outperform either humans or machines individually. I specialize in human-machine collaboration in recruiting and selecting talented groups of people.

The last decades have witnessed significant progress in machine learning with a host of applications of algorithmic decision-making in different safety-critical domains, such as medical, law, education, and transportation. In high-stake domains, machine learning predictions have far-reaching consequences on the end-users. With the aim of applying machine learning for societal goods, there have been increasing efforts to regulate machine learning by imposing interpretability, fairness, robustness, etc. in predictions. Towards responsible and trustworthy machine learning, we propose two research themes in our dissertation research: interpretability and fairness of machine learning classifiers. In particular, we design algorithms to learn interpretable rule-based classifiers, formally verify fairness, and explain the sources of unfairness. Prior approaches to these problems are often limited by scalability, accuracy, or both. To overcome these limitations, we closely integrate automated reasoning, formal methods, and statistics with fairness and interpretability to develop scalable and accurate solutions.

Fairness and stability are normative concepts that have been investigated for many social choice domains. Recently, increasing attention has fallen on richer, and more complex, settings and we look to develop, and study in depth, these fairness and stability notions in a variety of such complex domains.

Since the dawn of Transformer-based models, the trade-off between transparency and accuracy has been a topical issue in the NLP community. Working towards ethical and transparent automated content moderation (ACM), my goal is to find where it is still relevant to implement linguistic expertise. I show that transparent statistical models based on linguistic knowledge can still be competitive, while linguistic features have many other useful applications.

My thesis consists of investigating how chest X-ray images, radiologists’ eye movements and patients’ clinical data can be used to teach a machine how radiologists read and classify images with the goal of creating human-centric AI architectures that can (1) capture radiologists’ search behavioural patterns using their eye-movements in order to improve classification in DL systems, and (2) automatically detect lesions in medical images using clinical data and eye tracking data. Heterogeneous data sources such as chest X-rays, radiologists’ eye movements, and patients’ clinical data can contribute to novel multimodal DL architectures that, instead of learning directly from images’ pixels, will learn human classification patterns encoded in both the eye movements of the images’ regions and patients’ medical history. In addition to a quantitative evaluation, I plan to conduct questionnaires with expert radiologists to understand the effectiveness of the proposed multimodal DL architecture.

Deep neural networks (DNNs) have gained huge attention over the last several years due to their promising results in various tasks. However, due to their large model size and over-parameterization, they are recognized as being computationally demanding. Therefore, deep learning models are not well-suited to applications with limited computational resources and battery life. Current solutions to reduce computation costs mainly focus on inference efficiency while being resource-intensive during training. This Ph.D. research aims to address these challenges by developing cost-effective neural networks that can achieve decent performance on various complex tasks using minimum computational resources during training and inference of the network.

Although object detection has achieved impressive progress and has a broad impact, it still encounters significant challenges in accurately detecting objects in open-world scenarios. The data in real-world open scenes often exhibit characteristics of limited annotations, such as very few annotated samples or even unknown classes with no annotations. Our studies mainly focus on applying detection to various open scenes and addressing the challenges of sparse samples and unknown classes. The comprehensive research aims to develop more powerful and efficient methods for object detection in the open world, making them more suitable for real-world applications.

Causal reasoning reflects how humans perceive events in the world and establish relationships among them, identifying some as causes and others as effects. Causal discovery is about agreeing on these relationships and drawing them as a causal graph. Argumentation is the way humans reason systematically about an idea: the medium we use to exchange opinions, to get to know and trust each other and possibly agree on controversial matters. Developing AI which can argue with humans about causality would allow us to understand and validate the analysis of the AI and would allow the AI to bring evidence for or against humans’ prior knowledge. This is the goal of this project: to develop a novel scientific paradigm of interactive causal discovery and train AI to recognise causes and effects by debating, with humans, the results of different statistical methods

After several years of inquiry, realising trustworthy AI research in real-world systems remains difficult. Challenges include limited support for practical implementation, the need to facilitate multi-disciplinary human collaboration, and a lack of methods for holistic evaluation of trustworthy AI systems. This work proposes to augment research on trustworthy AI with research on responsible design practices to account for the socio-technical realities of developing AI systems. This study contributes to research on responsible design practice for trustworthy AI by developing design patterns for detecting and mitigating bias in voice-activated Edge AI applications.

More and more information is shared on the web or on social media platforms, and the information provided can be conflicting. In this case, we need to decide which information is reliable and should be taken into account. We want to define measures of reliability for each source that provides information, but also to find the truth among the conflicting information, and propose properties of these measures.

While many forms of belief change exist, relationship between belief revision and human reasoning is of primary interest in this work. The theory of belief revision extends classical two-valued logic with an approach to resolve the conflict between a set of beliefs and newly learned information. The goal of this project is to test how humans revise conflicting beliefs. Experiments are proposed in which human subjects are required to resolve conflicting beliefs via relevance and confidence. In our analysis, the human responses will be evaluated against the predictions of two perspectives of propositional belief revision: formal and psychological.

The growing population has accelerated the process of urbanisation, and is putting under stress the urban transport infrastructure. This results in increased traffic congestion, with significant health, economy, and social issues. Artificial Intelligence techniques are increasingly demonstrating their capabilities in predicting and supporting urban traffic control, by extending the abilities of traffic authorities in planning and reacting to different traffic conditions. In this context, our main research topic fits in the autonomic traffic control theme, with the aim of supporting the design of autonomous traffic control systems.

The availability of a large amount of unstructured text has generated interest in utilizing it for future decision-making and developing strategies in various critical domains. Despite some progress, automatically generating accurate reasoning models from the raw text is still an active area of research. Furthermore, most proposed approaches focus on a specific do-main. As such, their suggested transformation methods are usually unreliable when applied to other domains. This research aims to develop a framework, SCANER (Semi-automated CAusal Network Extraction from Raw text), to convert raw text into Causal Bayesian Networks (CBNs). The framework will then be employed in various domains to demonstrate its utilization as a decision-support tool. The preliminary experiments have focused on three domains: political narratives, food insecurity, and medical sciences. The future focus is on developing BNs from political narratives and modifying them through various methods to reduce the level of aggressiveness or extremity in the narratives without causing conflict among the masses or countries.

My PhD research deals with the use of Liquid Democracy (LD) for social choice scenarios, while considering the scarcity of attention as a driving factor. My aim is to better understand LD: theoretically as well as practically; in particular, by establishing containment in certain computational classes for corresponding combinatorial problems, suggesting methods to improve the use of LD, and understand its adaptation to specific scenarios. Concretely, I consider the use of LD as a solution for the problem of low voter attention in light of the high cognitive effort needed by voters to actively participate in voting processes.

The vast diversity of internal designs of taskable black-box AI systems and their nuanced zones of safe functionality make it difficult for a layperson to use them without unintended side effects. The focus of my dissertation is to develop paradigms that would enable a user to assess and understand the limits of an AI system’s safe operability. We develop a personalized AI assessment module that lets an AI system execute instruction sequences in simulators and answer queries about these executions. Our results show that such a primitive query-response capability is sufficient to efficiently derive a user-interpretable model of the system’s capabilities in fully observable settings.

Although state-of-the-art hierarchical robot planning algorithms allow robots to efficiently compute long-horizon motion plans for achieving user desired tasks, these methods typically rely upon environment-dependent state and action abstractions that need to be hand-designed by experts. On the other hand, non-hierarchical robot planning approaches fail to compute solutions for complex tasks that require reasoning over a long horizon. My research addresses these problems by proposing an approach for learning abstractions and developing hierarchical planners that efficiently use learned abstractions to boost robot planning performance and provide strong guarantees of reliability.

Multilingual Intent Detection and explore its different characteristics are major field of study for last few years. But, detection of intention dynamics from text or voice, especially in the Indian multilingual contexts, is a challenging task. So, my first research question is on intent detection and then I work on the application in Indian Multilingual Healthcare scenario. Speech dialogue systems are designed by a pre-defined set of intents to perform user specified tasks. Newer intentions may surface over time that call for retraining. However, the newer intents may not be explicitly announced and need to be inferred dynamically. Hence, here are two crucial jobs: (a) recognizing newly emergent intents; and (b) annotating the data of the new intents in order to effectively retrain the underlying classifier. The tasks become specially challenging when a large number of new intents emerge simultaneously and there is a limited budget of manual annotation. We develop MNID (Multiple Novel Intent Detection), a cluster based framework that can identify multiple novel intents while optimized human annotation cost. Empirical findings on numerous benchmark datasets (of varying sizes) show that MNID surpasses the baseline approaches in terms of accuracy and F1-score by wisely allocating the budget for annotation. We apply intent detection approach on different domains in Indian multilingual scenarios – healthcare, finance etc. The creation of advanced NLU healthcare systems is threatened by the lack of data and technology constraints for resource-poor languages in developing nations like India. We evaluate the current state of several cutting-edge language models used in the healthcare with the goal of detecting query intents and corresponding entities. We conduct comprehensive trials on a number of models different realistic contexts, and we investigate the practical relevance depending on budget and the availability of data on English.

Sequential decision making is an important field in machine learning, encompassing techniques such as online optimization, structured bandits, and reinforcement learning, which have numerous applications such as recommendation systems, online advertising, conversational agents, and robot learning. However, two key challenges face real-world sequential decision making: the need for adaptable models and the need for safety during both learning and execution. Adaptability refers to the ability of a model to quickly adapt to new and diverse environments, which is especially challenging in environments where feedback is sparse. To address this challenge, we propose using meta reinforcement learning with sub-optimal demonstration data. Safety is also critical in real-world sequential decision making. A model that adheres to safety requirements can avoid dangerous outcomes and ensure the safety of humans and other agents in the environment. We propose an approach based on online convex optimization that ensures safety at every time step. Addressing these challenges can lead to the development of more robust, safe, and adaptable AI systems that can perform a wide range of tasks and operate in a variety of environments.

I am a 3rd-year computer science PhD student at the University of Zurich. I would like to pursue my interest by applying for the IJCAI 2023 doctoral consortium. In my PhD, I combine computer science and philosophy for theoretical and empirical analyses to study the fairness of algorithmic decision-making systems. The goal is to reduce the risk of having a biased algorithmic decision-making systems, assuming that this would be harmful to society. To do that, I focus on supervised ML used to inform binary decision making. I investigate both the identification and the mitigation of bias (i.e., unfairness) in such systems. In the future, I intend to continue with my interdisciplinary work. More specifically, I am planning to investigate the temporal dynamics of ML-based decision-making systems and their effects on the evolvement of bias over time. I hope to develop novel solutions that ensure efficient, effective, and most importantly equitable long-term solutions that can cope with temporal distributions shift (e.g., of the target variable). In addition to that, I am working on applying the theoretical solutions to real world use cases, such as homelessness prevention using predictive analytics to detect people at high risk, ensuring fairer advertisement impressions on online ad platforms, using risk predictions models for insurance pricing without discriminating insured individuals.