Abstract

We motivate weakly supervised learning as an effective learning paradigm for problems where curating perfectly annotated datasets is expensive and may require domain expertise such as fine-grained classification. We focus on Partial Label Learning (PLL), a weakly-supervised learning paradigm where each training instance is paired with a set of candidate labels (partial label), one of which is the true label. Noisy PLL (NPLL) relaxes this constraint by allowing some partial labels to not contain the true label, enhancing the practicality of the problem. Our work centres on NPLL and presents a framework that initially assigns pseudo-labels to images by exploiting the noisy partial labels through a weighted nearest neighbour algorithm. These pseudo-label and image pairs are then used to train a deep neural network classifier with label smoothing. The classifier's features and predictions are subsequently employed to refine and enhance the accuracy of pseudo-labels. We perform thorough experiments on seven datasets and compare against nine NPLL and PLL methods. We achieve state-of-the-art results in all studied settings from the prior literature, obtaining substantial gains in the simulated fine-grained benchmarks. Further, we show the promising generalisation capability of our framework in realistic, fine-grained, crowd-sourced datasets.

Abstract

Line-search methods are commonly used to solve optimization problems. The simplest line search method is steepest descent where one always moves in the direction of the negative gradient. Newton's method on the other hand is a second-order method that uses the curvature information in the Hessian to pick the descent direction. In this work, we propose a new line-search method called Constrained Gradient Descent (CGD) that implicitly changes the landscape of the objective function for efficient optimization. CGD is formulated as a solution to the constrained version of the original problem where the constraint is on a function of the gradient. We optimize the corresponding Lagrangian function thereby favourably changing the landscape of the objective function. This results in a line search procedure where the Lagrangian penalty acts as a control over the descent direction and can therefore be used to iterate over points that have smaller gradient values, compared to iterates of vanilla steepest descent. We establish global linear convergence rates for CGD and provide numerical experiments on synthetic test functions to illustrate the performance of CGD. We also provide two practical variants of CGD, CGD-FD which is a Hessian free variant and CGD-QN, a quasi-Newton variant and demonstrate their effectiveness.

Abstract

The detrimental impact of the long-overdue pandemic has been widely acknowledged. However, the varied responses to its unprecedented challenges, particularly among young adults in college, are not well known. This study explores the role of psychological immunity in COVID-related trauma among Indian students. A significant proportion of students reported psychological distress, depression, and stress during the second wave between May and June 2021, with COVID-19 infection and related worries correlating with poorer mental health. Mediation analysis indicated that psychological flexibility negatively predicted distress, depression, and stress, while avoidance coping strategies showed a positive association with these outcomes. These findings suggest that psychological flexibility serves as a protective buffer against the impact of the pandemic, fostering resilience, while avoidant coping exacerbates its adverse effects. Interventions like Acceptance and Commitment Therapy (ACT) may enhance psychological flexibility and mitigate maladaptive coping, improving student mental well-being.

Abstract

Word-level prominence plays a crucial role in spoken language understanding, as it helps to interpret the speaker’s intent. However, automatic word-level prominence detection remains underexplored, particularly in non-native speech, where prominence patterns are more variable due to native language influence. While prominence is determined by acoustic features such as energy, duration, and pitch, capturing statistics on these acoustics at the word level provides only a global representation, missing finer suprasegmental variations. In this study, we consider syllables as the suprasegmental unit and propose a methodology that jointly models syllable prominence variations and their contribution to word prominence using sequential neural networks. This enables learning word-level prominence representations with minimal labeled data. Our method outperforms an unsupervised n-gram-based baseline by 24.01% and a supervised SVM by 5.73%, demonstrating its effectiveness over both approaches.

Abstract

We consider the problem of single-source domain generalization. Existing methods typically rely on extensive augmentations to synthetically cover diverse domains during training. However, they struggle with semantic shifts (e.g., background and viewpoint changes), as they often learn global features instead of local concepts that tend to be domain invariant. To address this gap, we propose an approach that compels models to leverage such local concepts during prediction. Given no suitable dataset with per-class concepts and localization maps exists, we first develop a novel pipeline to generate annotations by exploiting the rich features of diffusion and large-language models. Our next innovation is TIDE, a novel training scheme with a concept saliency alignment loss that ensures model focus on the right per-concept regions and a local concept contrastive loss that promotes learning domain-invariant concept representations. This not only gives a robust model but also can be visually interpreted using the predicted concept saliency maps. Given these maps at test time, our final contribution is a new correction algorithm that uses the corresponding local concept representations to iteratively refine the prediction until it aligns with prototypical concept representations that we store at the end of model training. We evaluate our approach extensively on four standard DG benchmark datasets and substantially outperform the current state-of-the-art (12% improvement on average) while also demonstrating that our predictions can be visually interpreted.

Abstract

Machine learning methods have seen a meteoric rise in their applications in the scientific community. However, little effort has been put into understanding these “black box” models. We show how one can apply integrated gradients (IGs) to understand these models by designing different baselines, by taking an example case study in particle physics. We find that the zero-vector baseline does not provide good feature attributions and that an averaged baseline sampled from the background events provides consistently more reasonable attributions.

Abstract

For people with hearing impairments, lipreading is a crucial skill, as it bridges the gap between spoken language and understanding, improving the ability to communicate effectively. However, the creation of lipreading resources is pervasive and labor-intensive, leading to a scarcity of high-quality, structured, and widely accessible educational materials. To address this, we developed LipMOOC, a Massive Open Online Course (MOOC) tailored for lipreading education. Our approach leverages synthetically generated content, reducing the dependence on human-recorded videos and building an accessible and effective learning option. Using the state-of-the-art models, we created a comprehensive lipreading course and conducted a study to evaluate its effectiveness. We statistically proved that (1) Synthetic videos can replace human-recorded videos without affecting the learning outcomes, and (2) Learner performance on a structured course, i.e., LipMOOC, is much better than a standard course. A total of 120 participants with hearing impairment and no prior lipreading experience volunteered. These results highlight the potential of AI-driven content generation and scientific instructional design.

Abstract

Submodular functions are known to satisfy various forms of fractional subadditivity. This work investigates the conditions for equality to hold exactly or approximately in the fractional subadditivity of submodular functions. We establish that a small gap in the inequality implies that the function is close to being modular, and that the gap is zero if and only if the function is modular. We then present natural implications of these results for special cases of submodular functions, such as entropy, relative entropy, and matroid rank. As a consequence, we characterize the necessary and sufficient conditions for equality to hold in Shearer's lemma, recovering a result of Ellis et al. (2016) as a special case. We leverage our results to propose a new multivariate mutual information, which generalizes Watanabe's total correlation (1960), Han's dual total correlation (1975), and Csiszar and Narayan's shared information (2004), and analyze its properties. Among these properties, we extend Watanabe's characterization of total correlation as the maximum correlation over partitions to fractional partitions. When applied to matrix determinantal inequalities for positive definite matrices, our results recover the equality conditions of the classical determinantal inequalities of Hadamard, Szasz, and Fischer as special cases.

Abstract

Foundational Language Models perform significantly better on downstream tasks in specialised domains (such as law, computer science, and medical science) upon being further pre-trained on extensive domain-specific corpora, but this continual pre-training incurs heavy computational costs. Indeed, some of the most performant specialised language models such as BioBERT incur even higher computing costs during domain-specific training than the pre-training cost of the foundational models they are initialised from. In this paper, we argue that much of the extended pre-training is redundant, with models seemingly wasting valuable resources re-learning lexical and semantic patterns already well-represented in their foundational models such as BERT, T5 and GPT. Focusing on Masked Language Models, we introduce a novel domain-specific masking strategy that is designed to facilitate continual learning while minimizing the training cost. Using this approach, we train and present a BERT-based model trained on a biomedical corpus that matches or surpasses traditionally trained biomedical language models in performance across several downstream classification tasks while incurring up to 11 times lower training costs.

Abstract

Foundational Language Models perform significantly better on downstream tasks in the biomedical domain upon being further pre-trained on extensive biomedical corpora, but this continual pre-training incurs heavy computational costs. Indeed, some of the most performant biomedical language models incur even more computing costs during domain-specific training than the entire training cost of the foundational models they are warm-started from. In this paper, we argue that much of the extended pre-training is redundant, with models seemingly wasting valuable resources re-learning lexical and semantic patterns already well-represented in their foundational models such as BERT, T5 and GPT. Focusing on Masked Language Models, we introduce a novel domain-specific masking strategy that is designed to facilitate continual learning while minimizing the training cost. Using this approach, we train and present a BERT-based model that matches or surpasses traditionally trained biomedical language models in performance across several downstream classification tasks while incurring up to 11 times lower training costs.