Related papers: RELAX: Representation Learning Explainability

Deep learning has achieved remarkable success in processing and managing unstructured data. However, its "black box" nature imposes significant limitations, particularly in sensitive application domains. While existing interpretable machine…

Unsupervised representation learning with variational inference relies heavily on independence assumptions over latent variables. Causal representation learning (CRL), however, argues that factors of variation in a dataset are, in fact,…

Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and…

Recent work has demonstrated the promise of combining local explanations with active learning for understanding and supervising black-box models. Here we show that, under specific conditions, these algorithms may misrepresent the quality of…

Deep Learning has become overly complicated and has enjoyed stellar success in solving several classical problems like image classification, object detection, etc. Several methods for explaining these decisions have been proposed. Black-box…

The application of unsupervised learning approaches, and in particular of clustering techniques, represents a powerful exploration means for the analysis of network measurements. Discovering underlying data characteristics, grouping similar…

Recent advances in large language models have demonstrated the promise of unsupervised reinforcement learning (RL) methods for enhancing reasoning capabilities without external supervision. However, the generalizability of these label-free…

In-context learning (ICL) has emerged as a successful paradigm for leveraging large language models (LLMs). However, it often struggles to generalize beyond the distribution of the provided demonstrations. A recent advancement in enhancing…

Learning effective representations in image-based environments is crucial for sample efficient Reinforcement Learning (RL). Unfortunately, in RL, representation learning is confounded with the exploratory experience of the agent -- learning…

Unsupervised representation learning approaches aim to learn discriminative feature representations from unlabeled data, without the requirement of annotating every sample. Enabling unsupervised representation learning is extremely crucial…

This review addresses the problem of learning abstract representations of the measurement data in the context of Deep Reinforcement Learning (DRL). While the data are often ambiguous, high-dimensional, and complex to interpret, many…

Recognizing relations between entities is a pivotal task of relational learning. Learning relation representations from distantly-labeled datasets is difficult because of the abundant label noise and complicated expressions in human…

Human-centric visual tasks have attracted increasing research attention due to their widespread applications. In this paper, we aim to learn a general human representation from massive unlabeled human images which can benefit downstream…

Disentangled Representation Learning (DRL) aims to learn a model capable of identifying and disentangling the underlying factors hidden in the observable data in representation form. The process of separating underlying factors of variation…

Unsupervised methods for learning distributed representations of words are ubiquitous in today's NLP research, but far less is known about the best ways to learn distributed phrase or sentence representations from unlabelled data. This…

Semi-supervised segmentation tackles the scarcity of annotations by leveraging unlabeled data with a small amount of labeled data. A prominent way to utilize the unlabeled data is by consistency training which commonly uses a…

Multi-view methods learn representations by aligning multiple views of the same image and their performance largely depends on the choice of data augmentation. In this paper, we notice that some other useful augmentations, such as image…

Learning by self-explanation is an effective learning technique in human learning, where students explain a learned topic to themselves for deepening their understanding of this topic. It is interesting to investigate whether this…

Semi-supervised learning holds great promise for many real-world applications, due to its ability to leverage both unlabeled and expensive labeled data. However, most semi-supervised learning algorithms still heavily rely on the limited…

The current state-of-the-art in many natural language processing and automated knowledge base completion tasks is held by representation learning methods which learn distributed vector representations of symbols via gradient-based…