Search results

We introduce Robust Training with Trust Scores (RT2S), a framework to train machine learning classifiers with potentially noisy labels. RT2S calculates a trust score for each training sample, which indicates the quality of its corresponding label. These trust scores are employed as sample weights during training and optionally during threshold optimization. The trust scores are generated from two sources

Rapid growth of deep learning models in recent years for robot and fraud detection has led to significant improvement in precision and recall but has also created a challenge for explainability and trust in the model decisions. In this paper, we propose a scalable multitiered framework that generates explainable network request level signatures for crawler bots on a large e-commerce advertising program.

Amodal perception requires inferring the full shape of an object that is partially occluded. This task is particularly challenging on two levels: (1) it requires more information than what is contained in the instant retina or imaging sensor, (2) it is difficult to obtain enough well-annotated amodal labels for supervision. To this end, this paper develops a new framework of Self-supervised amodal Video

Automatic speech recognition (ASR) models with low-footprint are increasingly being deployed on edge devices for conversational agents, which enhances privacy. We study the problem of federated continual incremental learning for recurrent neural network-transducer (RNN-T) ASR models in the privacy-enhancing scheme of learning on-device, without access to ground truth human transcripts or machine transcriptions

Building operations account for a significant portion of global emissions, contributing approximately 28% of global greenhouse gas emissions, according to the International Energy Agency. With the anticipated increase in cooling demand due to rising global temperatures, the optimization of rooftop units (RTUs) in buildings becomes crucial for reducing energy consumption and associated emissions. We focus

Recent work in scientific machine learning (SciML) has focused on incorporating partial differential equation (PDE) information into the learning process. Much of this work has focused on relatively “easy” PDE operators (e.g., elliptic and parabolic), with less emphasis on relatively “hard” PDE operators (e.g., hyperbolic). Within numerical PDEs, the latter problem class requires control of a type of volume

In this work, we show how to collect and use human feedback to improve complex models in information retrieval systems. Human feedback often improves model performance, yet little has been shown to combine human feedback and model tuning in an end-to-end setup with public resources. To this end, we develop a system called Crowd-Coachable Retriever (CCR),1 where we use crowd-sourced workers and open-source

With an ever-increasing number of smart edge devices with computation and communication constraints, Federated Learning (FL) is a promising paradigm for learning from distributed devices and their data. Typical approaches to FL aim to learn a single model that simultaneously performs well for all clients. But such an approach may be ineffective when the clients’ data distributions are heterogeneous. In

We consider the task of predicting subjective fashion traits from images using neural networks. Specifically, we are interested in training a network for ranking outfits according to how well they fit the user. In order to capture the variability induced by human subjective considerations, each training example is annotated by a panel of fashion experts. Similarly to previous works on subjective data, the

KingFisher is a team of several graduate and undergraduate students from the University of Illinois, Urbana-Champaign led by faculty advisor Julia Hockenmaier.

Predictive modeling over relational databases (RDBs) powers applications in various domains, yet remains challenging due to the need to capture both cross-table dependencies and complex feature interactions. Recent Relational Deep Learning (RDL) methods automate feature engineering via message passing, while classical approaches like Deep Feature Synthesis (DFS) rely on predefined non-parametric aggregators

Training an object detector incrementally has hardly been explored. In this paper, we propose attentive feature distillation which leverages both bottom-up and top-down attentions to mitigate forgetting in incremental detection. Then, we systematically analyze the proposed distillation method in different scenarios across various domains and categories. We find out that, contrary to common understanding

Deep reinforcement learning algorithms often use two networks for value function optimization: an online network, and a target network that tracks the online network with some delay. Using two separate networks enables the agent to hedge against issues that arise when performing bootstrapping. In this paper we endow two popular deep reinforcement learning algorithms, namely DQN and Rainbow, with updates

UT Austin-Amazon Science Hub seeks to advance research in artificial intelligence, machine learning, and large language models.

We study the problem of Reinforcement Learning (RL) with linear function approximation, i.e. assuming the optimal action-value function is linear in a known d-dimensional feature mapping. Unfortunately, however, based on only this assumption, the worst case sample complexity has been shown to be exponential, even under a generative model. Instead of making further assumptions on the MDP or value functions

We present MaCLR, a novel method to explicitly perform cross-modal self-supervised video representations learning from visual and motion modalities. Compared to previous video representation learning methods that mostly focus on learning motion cues implicitly from RGB inputs, MaCLR enriches standard contrastive learning objectives for RGB video clips with a cross-modal learning objective between a Motion

Traditionally, Alexa has interpreted customer requests according to their intents and slots. If you say, “Alexa, play ‘What’s Going On?’ by Marvin Gaye,” the intent should be PlayMusic, and “‘What’s Going On?’” and “Marvin Gaye” should fill the slots SongName and ArtistName.

Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world. Allowing machine learning algorithms to derive this decomposition in an unsupervised way has become an important line of research. However, current methods are restricted to simulated data or require additional information in the form of motion or depth in order to successfully discover

Nowadays, as cameras are rapidly adopted in our daily routine, images of documents are becoming both abundant and prevalent. Unlike natural images that capture physical objects, document-images contain a significant amount of text with critical semantics and complicated layouts. In this work, we devise a generic unsupervised technique to learn multimodal affinities between textual entities in a document-image

This paper introduces MO-LightGBM, an open-source library built upon LightGBM, specifically designed to offer an integrated, versatile, and easily adaptable framework for Multi-objective Learning to Rank (MOLTR). MO-LightGBM supports diverse Multi-objective optimization (MOO) settings and incorporates 12 state-of-the-art optimization strategies. Its modular architecture enhances usability and flexibility