Related papers: Learning to Partially Defer for Sequences

The objective of this work is to improve the accuracy of building demand forecasting. This is a more challenging task than grid level forecasting. For the said purpose, we develop a new technique called recurrent transform learning (RTL).…

Deep Learning (DL) models can be used to tackle time series analysis tasks with great success. However, the performance of DL models can degenerate rapidly if the data are not appropriately normalized. This issue is even more apparent when…

Event suffix and remaining time prediction are sequence to sequence learning tasks. They have wide applications in different areas such as economics, digital health, business process management and IT infrastructure monitoring. Timestamped…

This paper describes the architecture and systems built towards solving the SemEval 2023 Task 2: MultiCoNER II (Multilingual Complex Named Entity Recognition) [1]. We evaluate two approaches (a) a traditional Conditional Random Fields model…

While machine learning models are usually assumed to always output a prediction, there also exist extensions in the form of reject options which allow the model to reject inputs where only a prediction with an unacceptably low certainty…

Language models (LMs) are increasingly used to build agents that can act autonomously to achieve goals. During this automatic process, agents need to take a series of actions, some of which might lead to severe consequences if incorrect…

Large Language Models (LLMs) have shown strong potential in generating natural language explanations for recommender systems. However, existing methods often overlook the sequential dynamics of user behavior and rely on evaluation metrics…

With the development of Human-AI Collaboration in Classification (HAI-CC), integrating users and AI predictions becomes challenging due to the complex decision-making process. This process has three options: 1) AI autonomously classifies,…

Two-stage Learning-to-Defer (L2D) enables optimal task delegation by assigning each input to either a fixed main model or one of several offline experts, supporting reliable decision-making in complex, multi-agent environments. However,…

Sequence-to-sequence learning with neural networks has become the de facto standard for sequence prediction tasks. This approach typically models the local distribution over the next word with a powerful neural network that can condition on…

Predictive models are omnipresent in automated and assisted decision making scenarios. But for the most part they are used as black boxes which output a prediction without understanding partially or even completely how different features…

Parameter-efficient fine-tuning (PEFT) methods are increasingly used with pre-trained language models (PLMs) for continual learning (CL). These methods typically involve training a PEFT module for each new task and employing…

In this thesis, we develop various techniques for working with sets in machine learning. Each input or output is not an image or a sequence, but a set: an unordered collection of multiple objects, each object described by a feature vector.…

The Transformer is a highly successful deep learning model that has revolutionised the world of artificial neural networks, first in natural language processing and later in computer vision. This model is based on the attention mechanism…

Accurate prediction of pedestrians' future motions is critical for intelligent driving systems. Developing models for this task requires rich datasets containing diverse sets of samples. However, the existing naturalistic trajectory…

Large language models (LLMs) have demonstrated impressive performance on several tasks and are increasingly deployed in real-world applications. However, especially in high-stakes settings, it becomes vital to know when the output of an LLM…

Transformer-based models have gained large popularity and demonstrated promising results in long-term time-series forecasting in recent years. In addition to learning attention in time domain, recent works also explore learning attention in…

We introduce a new protocol for prediction with expert advice in which each expert evaluates the learner's and his own performance using a loss function that may change over time and may be different from the loss functions used by the…

Learning under one-sided feedback (i.e., where we only observe the labels for examples we predicted positively on) is a fundamental problem in machine learning -- applications include lending and recommendation systems. Despite this, there…

Selective Prediction is the task of rejecting inputs a model would predict incorrectly on. This involves a trade-off between input space coverage (how many data points are accepted) and model utility (how good is the performance on accepted…