相关论文: Model Compression for Domain Adaptation through Ca…

Domain adaptation aims to enable Large Language Models (LLMs) to generalize domain datasets unseen effectively during the training phase. However, factors such as the size of the model parameters and the scale of training data are general…

Most unsupervised anomaly detection methods based on representations of normal samples to distinguish anomalies have recently made remarkable progress. However, existing methods only learn a single decision boundary for distinguishing the…

The deep neural network (DNN) based speech enhancement approaches have achieved promising performance. However, the number of parameters involved in these methods is usually enormous for the real applications of speech enhancement on the…

While pretrained language models have exhibited impressive generalization capabilities, they still behave unpredictably under certain domain shifts. In particular, a model may learn a reasoning process on in-domain training data that does…

We study model pruning methods applied to Transformer-based neural network language models for automatic speech recognition. We explore three aspects of the pruning frame work, namely criterion, method and scheduler, analyzing their…

Accurately estimating personalized treatment effects within a study site (e.g., a hospital) has been challenging due to limited sample size. Furthermore, privacy considerations and lack of resources prevent a site from leveraging…

Feature compression is increasingly important for improving the efficiency of downstream tasks, especially in applications involving large-scale or multi-modal data. While existing methods typically rely on dedicated models for achieving…

Fine-tuning pre-trained language models improves the quality of commercial reply suggestion systems, but at the cost of unsustainable training times. Popular training time reduction approaches are resource intensive, thus we explore…

Generative recommendation has recently emerged as a promising paradigm for sequential recommendation. It formulates the task as an autoregressive generation process, predicting tokens of the next item conditioned on user interaction…

Existing multi-objective preference alignment methods for large language models (LLMs) face limitations: (1) the inability to effectively balance various preference dimensions, and (2) reliance on auxiliary reward/reference models…

How will the climate system respond to anthropogenic forcings? One approach to this question relies on climate model projections. Current climate projections are considerably uncertain. Characterizing and, if possible, reducing this…

Automated decision-making (ADM) systems are being deployed across a diverse range of critical problem areas such as social welfare and healthcare. Recent work highlights the importance of causal ML models in ADM systems, but implementing…

This paper presents a novel pre-trained language models (PLM) compression approach based on the matrix product operator (short as MPO) from quantum many-body physics. It can decompose an original matrix into central tensors (containing the…

Deployed machine learning models should be updated to take advantage of a larger sample size to improve performance, as more data is gathered over time. Unfortunately, even when model updates improve aggregate metrics such as accuracy, they…

Machine translation models struggle when translating out-of-domain text, which makes domain adaptation a topic of critical importance. However, most domain adaptation methods focus on fine-tuning or training the entire or part of the model…

Automated audio captioning (AAC) is the task of automatically generating textual descriptions for general audio signals. A captioning system has to identify various information from the input signal and express it with natural language.…

Considering censored outcomes in survival analysis can lead to quite complex results in the model setting of causal inference. Causal inference has attracted a lot of attention over the past few years, but little research has been done on…

Aspect Sentiment Triplet Extraction (ASTE) is a challenging task in sentiment analysis, aiming to provide fine-grained insights into human sentiments. However, existing benchmarks are limited to two domains and do not evaluate model…

There is growing interest in extending average treatment effect (ATE) estimation to incorporate non-tabular data, such as images and text, which may act as sources of confounding. Neglecting these effects risks biased results and flawed…

Accurate estimation of conditional average treatment effects (CATE) is at the core of personalized decision making. While there is a plethora of models for CATE estimation, model selection is a nontrivial task, due to the fundamental…