Acoustic scene classification (ASC) is a crucial research problem in computational auditory scene analysis, and it aims to recognize the unique acoustic characteristics of an environment. One of the challenges of the ASC task is domain shift caused by a distribution gap between training and testing data. Since 2018, ASC challenges have focused on the generalization of ASC models across different recording devices. Although this task in recent years has achieved substantial progress in device generalization, the challenge of domain shift between different regions, involving characteristics such as time, space, culture, and language, remains insufficiently explored at present. In addition, considering the abundance of unlabeled acoustic scene data in the real world, it is important to study the possible ways to utilize these unlabelled data. Therefore, we introduce the task Semi-supervised Acoustic Scene Classification under Domain Shift in the ICME 2024 Grand Challenge. We encourage participants to innovate with semi-supervised learning techniques, aiming to develop more robust ASC models under domain shift.

In contrast to classical cognitive science which studied brains in isolation, ecological approaches focused on the role of the body and environment in shaping cognition. Similarly, in this thesis we adopt an ecological approach to grounded natural language understanding (NLU) research. Grounded language understanding studies language understanding systems situated in the context of events, actions and precepts in naturalistic/simulated virtual environments. Where classic research tends to focus on designing new models and optimization methods while treating environments as given, we explore the potential of environment design for improving data collection and model development. We developed novel training and annotation approaches for procedural text understanding based on text-based game environments. We also drew upon embodied cognitive linguistics literature to propose a roadmap for grounded NLP research, and to inform the development of a new benchmark for measuring the progress of large language models on challenging commonsense reasoning tasks. We leveraged the richer supervision provided by text-based game environments to develop Breakpoint Transformers, a novel approach to modeling intermediate semantic information in long narrative or procedural texts. Finally, we integrated theories on the role of environments in collective human intelligence to propose a design for AI-augmented "social thinking environments" for knowledge workers like scientists.

Offline reinforcement learning (RL) has seen notable advancements through return-conditioned supervised learning (RCSL) and value-based methods, yet each approach comes with its own set of practical challenges. Addressing these, we propose Value-Aided Conditional Supervised Learning (VCS), a method that effectively synergizes the stability of RCSL with the stitching ability of value-based methods. Based on the Neural Tangent Kernel analysis to discern instances where value function may not lead to stable stitching, VCS injects the value aid into the RCSL's loss function dynamically according to the trajectory return. Our empirical studies reveal that VCS not only significantly outperforms both RCSL and value-based methods but also consistently achieves, or often surpasses, the highest trajectory returns across diverse offline RL benchmarks. This breakthrough in VCS paves new paths in offline RL, pushing the limits of what can be achieved and fostering further innovations.

Weakly supervised learning generally faces challenges in applicability to various scenarios with diverse weak supervision and in scalability due to the complexity of existing algorithms, thereby hindering the practical deployment. This paper introduces a general framework for learning from weak supervision (GLWS) with a novel algorithm. Central to GLWS is an Expectation-Maximization (EM) formulation, adeptly accommodating various weak supervision sources, including instance partial labels, aggregate statistics, pairwise observations, and unlabeled data. We further present an advanced algorithm that significantly simplifies the EM computational demands using a Non-deterministic Finite Automaton (NFA) along with a forward-backward algorithm, which effectively reduces time complexity from quadratic or factorial often required in existing solutions to linear scale. The problem of learning from arbitrary weak supervision is therefore converted to the NFA modeling of them. GLWS not only enhances the scalability of machine learning models but also demonstrates superior performance and versatility across 11 weak supervision scenarios. We hope our work paves the way for further advancements and practical deployment in this field.

We present TartanDrive 2.0, a large-scale off-road driving dataset for self-supervised learning tasks. In 2021 we released TartanDrive 1.0, which is one of the largest datasets for off-road terrain. As a follow-up to our original dataset, we collected seven hours of data at speeds of up to 15m/s with the addition of three new LiDAR sensors alongside the original camera, inertial, GPS, and proprioceptive sensors. We also release the tools we use for collecting, processing, and querying the data, including our metadata system designed to further the utility of our data. Custom infrastructure allows end users to reconfigure the data to cater to their own platforms. These tools and infrastructure alongside the dataset are useful for a variety of tasks in the field of off-road autonomy and, by releasing them, we encourage collaborative data aggregation. These resources lower the barrier to entry to utilizing large-scale datasets, thereby helping facilitate the advancement of robotics in areas such as self-supervised learning, multi-modal perception, inverse reinforcement learning, and representation learning. The dataset is available at https://github.com/castacks/tartan drive 2.0.

Language models deployed in the wild make errors. However, simply updating the model with the corrected error instances causes catastrophic forgetting -- the updated model makes errors on instances learned during the instruction tuning or upstream training phase. Randomly replaying upstream data yields unsatisfactory performance and often comes with high variance and poor controllability. To this end, we try to forecast upstream examples that will be forgotten due to a model update for improved controllability of the replay process and interpretability. We train forecasting models given a collection of online learned examples and corresponding forgotten upstream pre-training examples. We propose a partially interpretable forecasting model based on the observation that changes in pre-softmax logit scores of pretraining examples resemble that of online learned examples, which performs decently on BART but fails on T5 models. We further show a black-box classifier based on inner products of example representations achieves better forecasting performance over a series of setups. Finally, we show that we reduce forgetting of upstream pretraining examples by replaying examples that are forecasted to be forgotten, demonstrating the practical utility of forecasting example forgetting.

Self-training has gained attraction because of its simplicity and versatility, yet it is vulnerable to noisy pseudo-labels caused by erroneous confidence. Several solutions have been proposed to handle the problem, but they require significant modifications in self-training algorithms or model architecture, and most have limited applicability in tabular domains. To address this issue, we explore a novel direction of reliable confidence in self-training contexts and conclude that the confidence, which represents the value of the pseudo-label, should be aware of the cluster assumption. In this regard, we propose Cluster-Aware Self-Training (CAST) for tabular data, which enhances existing self-training algorithms at a negligible cost without significant modifications. Concretely, CAST regularizes the confidence of the classifier by leveraging local density for each class in the labeled training data, forcing the pseudo-labels in low-density regions to have lower confidence. Extensive empirical evaluations on up to 21 real-world datasets confirm not only the superior performance of CAST but also its robustness in various setups in self-training contexts. Self-training is an iterative algorithm that trains a classifier using a pseudo-labeling procedure, which assigns pseudo-labels to unlabeled data to use as labeled data in each iteration. It is a simple and versatile semi-supervised learning method as it employs the identical training procedure used in supervised learning except for integrating pseudo-labels into the training data. Therefore, it is particularly useful for practitioners in tabular domains, where the dominant architectures are gradient boosting decision trees (GBDTs) which are provided as complete frameworks that do not allow any changes in the training procedure [28; 8; 50]. Contemporary self-training methods consider the confidence, often referred to as prediction probabilities of the classifier, as the score and generate a pseudo-label if the confidence score is higher than or equal to a certain threshold [63; 45]. However, it may not consistently serve as a reliable metric in real-world scenarios for various reasons such as biased classifiers or overconfidence in neural networks [22]. These erroneous confidence scores can lead to the generation of noisy pseudo-labels during the self-training iterations, which may introduce confirmation bias that undermines the final self-training performance [3]. Given these potential pitfalls, relying solely on the confidence may be a precarious choice [72; 47; 64]. Several studies have been conducted to improve erroneous confidence by calibrating the confidence to reflect its ground truth correctness likelihood [22].

The Smart home possesses the capability of facilitating home services to their users with the systematic advance in The Internet of Things (IoT) and information and communication technologies (ICT) in recent decades. The home service offered by the smart devices helps the users in utilize maximized level of comfort for the objective of improving life quality. As the user and smart devices communicate through an insecure channel, the smart home environment is prone to security and privacy problems. A secure authentication protocol needs to be established between the smart devices and the user, such that a situation for device authentication can be made feasible in smart home environments. Most of the existing smart home authentication protocols were identified to fail in facilitating a secure mutual authentication and increases the possibility of lunching the attacks of session key disclosure, impersonation and stolen smart device. In this paper, Secure Supervised Learning-based Smart Home Authentication Framework (SSL-SHAF) is proposed as are liable mutual authentication that can be contextually imposed for better security. The formal analysis of the proposed SSL-SHAF confirmed better resistance against session key disclosure, impersonation and stolen smart device attacks. The results of SSL-SHAF confirmed minimized computational costs and security compared to the baseline protocols considered for investigation.

Children learn powerful internal models of the world around them from a few years of egocentric visual experience. Can such internal models be learned from a child's visual experience with highly generic learning algorithms or do they require strong inductive biases? Recent advances in collecting large-scale, longitudinal, developmentally realistic video datasets and generic self-supervised learning (SSL) algorithms are allowing us to begin to tackle this nature vs. nurture question. However, existing work typically focuses on image-based SSL algorithms and visual capabilities that can be learned from static images (e.g. object recognition), thus ignoring temporal aspects of the world. To close this gap, here we train self-supervised video models on longitudinal, egocentric headcam recordings collected from a child over a two year period in their early development (6-31 months). The resulting models are highly effective at facilitating the learning of action concepts from a small number of labeled examples; they have favorable data size scaling properties; and they display emergent video interpolation capabilities. Video models also learn more robust object representations than image-based models trained with the exact same data. These results suggest that important temporal aspects of a child's internal model of the world may be learnable from their visual experience using highly generic learning algorithms and without strong inductive biases.

In Natural Language Processing, entity linking (EL) has centered around Wikipedia, but yet remains underexplored for the job market domain. Disambiguating skill mentions can help us get insight into the current labor market demands. In this work, we are the first to explore EL in this domain, specifically targeting the linkage of occupational skills to the ESCO taxonomy (le Vrang et al., 2014). Previous efforts linked coarse-grained (full) sentences to a corresponding ESCO skill. In this work, we link more fine-grained span-level mentions of skills. We tune two high-performing neural EL models, a bi-encoder (Wu et al., 2020) and an autoregressive model (Cao et al., 2021), on a synthetically generated mention--skill pair dataset and evaluate them on a human-annotated skill-linking benchmark. Our findings reveal that both models are capable of linking implicit mentions of skills to their correct taxonomy counterparts. Empirically, BLINK outperforms GENRE in strict evaluation, but GENRE performs better in loose evaluation (accuracy@$k$).