Related papers: Enhancing Continual Relation Extraction via Classi…

The standard loss function used to train neural network classifiers, categorical cross-entropy (CCE), seeks to maximize accuracy on the training data; building useful representations is not a necessary byproduct of this objective. In this…

Knowledge Bases (KBs) require constant up-dating to reflect changes to the world they represent. For general purpose KBs, this is often done through Relation Extraction (RE), the task of predicting KB relations expressed in text mentioning…

Joint extraction of entities and relations aims to detect entity pairs along with their relations using a single model. Prior work typically solves this task in the extract-then-classify or unified labeling manner. However, these methods…

Continual learning (CL) has spurred the development of several methods aimed at consolidating previous knowledge across sequential learning. Yet, the evaluations of these methods have primarily focused on the final output, such as changes…

In document-level relation extraction (DocRE), graph structure is generally used to encode relation information in the input document to classify the relation category between each entity pair, and has greatly advanced the DocRE task over…

Document-level relation extraction (DocRE) models generally use graph networks to implicitly model the reasoning skill (i.e., pattern recognition, logical reasoning, coreference reasoning, etc.) related to the relation between one entity…

Counterfactual explanations (CFE) for deep image classifiers aim to reveal how minimal input changes lead to different model decisions, providing critical insights for model interpretation and improvement. However, existing CFE methods…

Many deep learning architectures for semantic segmentation involve a Fully Convolutional Neural Network (FCN) followed by a Conditional Random Field (CRF) to carry out inference over an image. These models typically involve unary potentials…

Convolutional neural networks (CNNs) have achieved significant success in image classification by utilizing large-scale datasets. However, it is still of great challenge to learn from scratch on small-scale datasets efficiently and…

Learning rich representation from data is an important task for deep generative models such as variational auto-encoder (VAE). However, by extracting high-level abstractions in the bottom-up inference process, the goal of preserving all…

Deep learning has shown its human-level performance in various applications. However, current deep learning models are characterised by catastrophic forgetting of old knowledge when learning new classes. This poses a challenge particularly…

Latent features learned by deep learning approaches have proven to be a powerful tool for machine learning. They serve as a data abstraction that makes learning easier by capturing regularities in data explicitly. Their benefits motivated…

In continual learning (CL), the goal is to design models that can learn a sequence of tasks without catastrophic forgetting. While there is a rich set of techniques for CL, relatively little understanding exists on how representations built…

Knowledge-based question answering relies on the availability of facts, the majority of which cannot be found in structured sources (e.g. Wikipedia info-boxes, Wikidata). One of the major components of extracting facts from unstructured…

Training large-scale image recognition models is computationally expensive. This raises the question of whether there might be simple ways to improve the test performance of an already trained model without having to re-train or fine-tune…

Learning new information without forgetting prior knowledge is central to human intelligence. In contrast, neural network models suffer from catastrophic forgetting: a significant degradation in performance on previously learned tasks when…

Causal representation learning (CRL) offers the promise of uncovering the underlying causal model by which observed data was generated, but the practical applicability of existing methods remains limited by the strong assumptions required…

Residual connections are one of the most important components in neural network architectures for mitigating the vanishing gradient problem and facilitating the training of much deeper networks. One possible explanation for how residual…

An important aspect of deploying face recognition (FR) algorithms in real-world applications is their ability to learn new face identities from a continuous data stream. However, the online training of existing deep neural network-based FR…

Continual Learning (CL) is crucial for enabling networks to dynamically adapt as they learn new tasks sequentially, accommodating new data and classes without catastrophic forgetting. Diverging from conventional perspectives on CL, our…