Related papers: PAIR-Former: Budgeted Relational Multi-Instance Le…

Prior-Fitted Networks (PFNs) have recently been proposed to efficiently perform tabular classification tasks. Although they achieve good performance on small datasets, they encounter limitations with larger datasets. These limitations…

Federated Bayesian neural networks require fixing a prior on the model parameters together with a likelihood. Eliciting meaningful priors on the weight space of modern overparameterized models is notoriously difficult, and misspecification…

Pretrained foundation models offer substantial benefits for a wide range of downstream tasks, which can be one of the most potential techniques to access artificial general intelligence. However, scaling up foundation transformers for…

The full potential of large pretrained models remains largely untapped in control domains like robotics. This is mainly because of the scarcity of data and the computational challenges associated with training or fine-tuning these large…

Multi-instance learning (MIL) deals with objects represented as bags of instances and can predict instance labels from bag-level supervision. However, significant performance gaps exist between instance-level MIL algorithms and supervised…

Pre-trained Language Models (PLMs) can be accurately fine-tuned for downstream text processing tasks. Recently, researchers have introduced several parameter-efficient fine-tuning methods that optimize input prompts or adjust a small number…

Fine-tuning pre-trained language models for multiple tasks tends to be expensive in terms of storage. To mitigate this, parameter-efficient transfer learning (PETL) methods have been proposed to address this issue, but they still require a…

Multiple instance learning (MIL) is a form of weakly supervised learning where training instances are arranged in sets, called bags, and a label is provided for the entire bag. This formulation is gaining interest because it naturally fits…

Multiple Instance Learning (MIL) is a cornerstone approach in computational pathology (CPath) for generating clinically meaningful slide-level embeddings from gigapixel tissue images. However, MIL often struggles with small, weakly…

This paper presents a novel multitask multiple kernel learning framework that efficiently learns the kernel weights leveraging the relationship across multiple tasks. The idea is to automatically infer this task relationship in the…

Click-Through Rate (CTR) prediction holds a paramount position in recommender systems. The prevailing ID-based paradigm underperforms in cold-start scenarios due to the skewed distribution of feature frequency. Additionally, the utilization…

Token-level adaptive training approaches can alleviate the token imbalance problem and thus improve neural machine translation, through re-weighting the losses of different target tokens based on specific statistical metrics (e.g., token…

This paper introduces a novel approach for multi-task regression that connects Kernel Machines (KMs) and Extreme Learning Machines (ELMs) through the exploitation of the Random Fourier Features (RFFs) approximation of the RBF kernel. In…

Protein-ligand binding affinity (PLBA) prediction is the fundamental task in drug discovery. Recently, various deep learning-based models predict binding affinity by incorporating the three-dimensional structure of protein-ligand complexes…

The composed image retrieval (CIR) task aims to retrieve the desired target image for a given multimodal query, i.e., a reference image with its corresponding modification text. The key limitations encountered by existing efforts are two…

Multi-task Imitation Learning (MIL) aims to train a policy capable of performing a distribution of tasks based on multi-task expert demonstrations, which is essential for general-purpose robots. Existing MIL algorithms suffer from low data…

MicroRNAs (miRNAs) are non-coding RNAs with approximately 22 nucleotides (nt) that are derived from precursor molecules. These precursor molecules or pre-miRNAs often fold into stem-loop hairpin structures. However, a large number of…

Multiple instance learning (MIL) has attracted great attention recently in machine learning community. However, most MIL algorithms are very slow and cannot be applied to large datasets. In this paper, we propose a greedy strategy to speed…

Biological foundation models (BioFMs), pretrained on large-scale biological sequences, have recently shown strong potential in providing meaningful representations for diverse downstream bioinformatics tasks. However, such models often rely…

Ear recognition task is known as predicting whether two ear images belong to the same person or not. In this paper, we present a novel metric learning method for ear recognition. This method is formulated as a pairwise constrained…