An official website of the United States government
With the prevalence of machine learning in many high-stakes decision-making processes, e.g., hiring and admission, it is important to take fairness into account when practitioners design and deploy machine learning models, especially in scenarios with imperfectly labeled data. Multiple-Instance Learning (MIL) is a weakly supervised approach where instances are grouped in labeled bags, each containing several instances sharing the same label. However, current fairness-centric methods in machine learning often fall short when applied to MIL due to their reliance on instance-level labels. In this work, we introduce a Fair Multiple-Instance Learning (FMIL) framework to ensure fairness in weakly supervised learning. In particular, our method bridges the gap between bag-level and instance-level labeling by leveraging the bag labels, inferring high-confidence instance labels to improve both accuracy and fairness in MIL classifiers. Comprehensive experiments underscore that our FMIL framework substantially reduces biases in MIL without compromising accuracy.
more »
« less
TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning
Deep neural networks, including transformers and convolutional neural networks (CNNs), have significantly improved multivariate time series classification (MTSC). However, these methods often rely on supervised learning, which does not fully account for the sparsity and locality of patterns in time series data (e.g., quantification of diseases-related anomalous points in ECG and abnormal detection in signal). To address this challenge, we formally discuss and reformulate MTSC as a weakly supervised problem, introducing a novel multiple-instance learning (MIL) framework for better localization of patterns of interest and modeling time dependencies within time series. Our novel approach, TimeMIL, formulates the temporal correlation and ordering within a time-aware MIL pooling, leveraging a tokenized transformer with a specialized learnable wavelet positional token. The proposed method surpassed 26 recent state-of-the-art MTSC methods, underscoring the effectiveness of the weakly supervised TimeMIL in MTSC. The code is available https://github.com/xiwenc1/TimeMIL.
more »
« less
- Award ID(s):
- 2204721
- PAR ID:
- 10542207
- Publisher / Repository:
- ICML
- Date Published:
- ISSN:
- 2640-3498
- Format(s):
- Medium: X
- Location:
- Vienna, Austria
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Replay is the reactivation of one or more neural patterns that are similar to the activation patterns experienced during past waking experiences. Replay was first observed in biological neural networks during sleep, and it is now thought to play a critical role in memory formation, retrieval, and consolidation. Replay-like mechanisms have been incorporated in deep artificial neural networks that learn over time to avoid catastrophic forgetting of previous knowledge. Replay algorithms have been successfully used in a wide range of deep learning methods within supervised, unsupervised, and reinforcement learning paradigms. In this letter, we provide the first comprehensive comparison between replay in the mammalian brain and replay in artificial neural networks. We identify multiple aspects of biological replay that are missing in deep learning systems and hypothesize how they could be used to improve artificial neural networks.more » « less
-
Although social anxiety and depression are common, they are often under diagnosed and under treated, in part due to difficulties identifying and accessing individuals in need of services. Current assessments rely on client self-report and clinician judgment, which are vulnerable to social desirability and other subjective biases. Identifying objective, non-burdensome markers of these mental health problems, such as features of speech, could help advance assessment, prevention, and treatment approaches. Prior research examining speech detection methods has focused on fully supervised learning approaches employing strongly labeled data. However, strong labeling of individuals high in symptoms or state affect in speech audio data is impractical, in part because it is not possible to identify with high confidence which regions of a long speech indicate the person’s symptoms or affective state. We propose a weakly supervised learning framework for detecting social anxiety and depression from long audio clips. Specifically, we present a novel feature modeling technique named NN2Vec that identies and exploits the inherent relationship between speakers’ vocal states and symptoms/affective states. Detecting speakers high in social anxiety or depression symptoms using NN2Vec features achieves F-1 scores 17% and 13% higher than those of the best available baselines. In addition, we present a new multiple instance learning adaptation of a BLSTM classifier, named BLSTM-MIL. Our novel framework of using NN2Vec features with the BLSTM-MIL classifier achieves F-1 scores of 90.1% and 85.44% in detecting speakers high in social anxiety and depression symptoms.more » « less
-
Learning representations for individual instances when only bag-level labels are available is a fundamental challenge in multiple instance learning (MIL). Recent works have shown promising results using contrastive self-supervised learning (CSSL), which learns to push apart representations corresponding to two different randomly-selected instances. Unfortunately, in real-world applications such as medical image classification, there is often class imbalance, so randomly-selected instances mostly belong to the same majority class, which precludes CSSL from learning inter-class differences. To address this issue, we propose a novel framework, Iterative Self-paced Supervised Contrastive Learning for MIL Representations (ItS2CLR), which improves the learned representation by exploiting instance-level pseudo labels derived from the bag-level labels. The framework employs a novel self-paced sampling strategy to ensure the accuracy of pseudo labels. We evaluate ItS2CLR on three medical datasets, showing that it improves the quality of instance-level pseudo labels and representations, and outperforms existing MIL methods in terms of both bag and instance level accuracy. Code is available at this https URLmore » « less
-
Abstract Symbolic time series analysis (STSA) plays an important role in the investigation of continuously evolving dynamical systems, where the capability to interpret the joint effects of multiple sensor signals is essential for adequate representation of the embedded knowledge. This technical brief develops and validates, by simulation, an STSA-based algorithm to make timely decisions on dynamical systems for information fusion and pattern classification from ensembles of multisensor time series data. In this context, one of the most commonly used methods has been neural networks (NN) in their various configurations; however, these NN-based methods may require large-volume data and prolonged computational time for training. An alternative feasible method is the STSA-based probabilistic finite state automata (PFSA), which has been shown in recent literature to require significantly less training data and to be much faster than NN for training and, to some extent, for testing. This technical brief reports a modification of the current PFSA methods to accommodate (possibly heterogeneous and not necessarily tightly synchronized) multisensor data fusion and (supervised learning-based) pattern classification in real-time. Efficacy of the proposed method is demonstrated by fusion of time series of position and velocity sensor data, generated from a simulation model of the forced Duffing equation.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
