Related papers: Assessing Data Efficiency in Task-Oriented Semanti…

Data cleaning is a long-standing challenge in data management. While powerful logic and statistical algorithms have been developed to detect and repair data errors in tables, existing algorithms predominantly rely on domain-experts to first…

Mappings to structured output spaces (strings, trees, partitions, etc.) are typically learned using extensions of classification algorithms to simple graphical structures (eg., linear chains) in which search and parameter estimation can be…

For pixel-level crowd understanding, it is time-consuming and laborious in data collection and annotation. Some domain adaptation algorithms try to liberate it by training models with synthetic data, and the results in some recent works…

Background: We describe an informatics framework for researchers and clinical investigators to efficiently perform parameter sensitivity analysis and auto-tuning for algorithms that segment and classify image features in a large dataset of…

Sensing and communication are fundamental enablers of next-generation networks. While communication technologies have advanced significantly, sensing remains limited to conventional parameter estimation and is far from fully explored.…

Consider the communication-constrained problem of nonparametric function estimation, in which each distributed terminal holds multiple i.i.d. samples. Under certain regularity assumptions, we characterize the minimax optimal rates for all…

Sparse decision trees are one of the most common forms of interpretable models. While recent advances have produced algorithms that fully optimize sparse decision trees for prediction, that work does not address policy design, because the…

In the last decade, an impressive increase in software adaptions has led to a surge in log data production, making manual log analysis impractical and establishing the necessity for automated methods. Conversely, most automated analysis…

The intensity matching approach for tractable performance evaluation and optimization of cellular networks is introduced. It assumes that the base stations are modeled as points of a Poisson point process and leverages stochastic geometry…

Profiling techniques are used extensively at different parts of the computing stack to achieve many goals. One major goal is to make a piece of software execute more efficiently on a specific hardware platform, where efficiency spans…

Traditional domain adaptive semantic segmentation addresses the task of adapting a model to a novel target domain under limited or no additional supervision. While tackling the input domain gap, the standard domain adaptation settings…

Semantic communication aims to convey meaning rather than bit-perfect reproduction, representing a paradigm shift from traditional communication. This paper investigates distribution learning in semantic communication where receivers must…

Recently, pre-trained language models mostly follow the pre-train-then-fine-tuning paradigm and have achieved great performance on various downstream tasks. However, since the pre-training stage is typically task-agnostic and the…

Conformance checking techniques let us find out to what degree a process model and real execution data correspond to each other. In recent years, alignments have proven extremely useful in calculating conformance statistics. Most techniques…

Discrete representation has emerged as a powerful tool in task-oriented semantic communication (ToSC), offering compact, interpretable, and efficient representations well-suited for low-power edge intelligence scenarios. Its inherent…

The training of task-oriented dialogue systems is often confronted with the lack of annotated data. In contrast to previous work which augments training data through expensive crowd-sourcing efforts, we propose four different automatic…

With the emergence of large model-based agents, widely adopted transformer-based architectures inevitably produce excessively long token embeddings for transmission, which may result in high bandwidth overhead, increased power consumption…

This dissertation addresses visual scene understanding and enhances segmentation performance and generalization, training efficiency of networks, and holistic understanding. First, we investigate semantic segmentation in the context of…

Large-scale pre-training followed by downstream fine-tuning is an effective solution for transferring deep-learning-based models. Since finetuning all possible pre-trained models is computational costly, we aim to predict the…

Prediction is critical for decision-making under uncertainty and lends validity to statistical inference. With targeted prediction, the goal is to optimize predictions for specific decision tasks of interest, which we represent via…