Related papers: DSI++: Updating Transformer Memory with New Docume…

Modern computer vision applications suffer from catastrophic forgetting when incrementally learning new concepts over time. The most successful approaches to alleviate this forgetting require extensive replay of previously seen data, which…

In continual learning, there is a serious problem of catastrophic forgetting, in which previous knowledge is forgotten when a model learns new tasks. Various methods have been proposed to solve this problem. Replay methods which replay data…

The ability of humans to rapidly learn new knowledge while retaining old memories poses a significant challenge for current deep learning models. To handle this challenge, we draw inspiration from human memory and learning mechanisms and…

The intrusion detection system (IDS) is an essential element of security monitoring in computer networks. An IDS distinguishes the malicious traffic from the benign one and determines the attack types targeting the assets of the…

In a dynamic retrieval system, documents must be ingested as they arrive, and be immediately findable by queries. Our purpose in this paper is to describe an index structure and processing regime that accommodates that requirement for…

Continuously acquiring new knowledge from a dynamic environment is a fundamental capability for animals, facilitating their survival and ability to address various challenges. This capability is referred to as continual learning, which…

In incremental classification tasks for hyperspectral images, catastrophic forgetting is an unavoidable challenge. While memory recall methods can mitigate this issue, they heavily rely on samples from old categories. This paper proposes a…

Recently, retrieval systems based on dense representations have led to important improvements in open-domain question answering, and related tasks. While very effective, this approach is also memory intensive, as the dense vectors for the…

Healthcare clinics regularly encounter dynamic data that changes due to variations in patient populations, treatment policies, medical devices, and emerging disease patterns. Deep learning models can suffer from catastrophic forgetting when…

The emergence of learned indexes has caused a paradigm shift in our perception of indexing by considering indexes as predictive models that estimate keys' positions within a data set, resulting in notable improvements in key search…

Incremental learning attempts to develop a classifier which learns continuously from a stream of data segregated into different classes. Deep learning approaches suffer from catastrophic forgetting when learning classes incrementally, while…

For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the…

Large language model (LLM) agents have shown promising performance in generating code for solving complex data science problems. Recent studies primarily focus on enhancing in-context learning through improved search, sampling, and planning…

Recent work has shown that diffusion models memorize and reproduce training data examples. At the same time, large copyright lawsuits and legislation such as GDPR have highlighted the need for erasing datapoints from diffusion models.…

The concept of evolving intelligent system (EIS) provides an effective avenue for data stream mining because it is capable of coping with two prominent issues: online learning and rapidly changing environments. We note at least three…

Dense Retrieval (DR) models have proven to be effective for Document Retrieval and Information Grounding tasks. Usually, these models are trained and optimized for improving the relevance of top-ranked documents for a given query. Previous…

Catastrophic forgetting poses a substantial challenge for managing intelligent agents controlled by a large model, causing performance degradation when these agents face new tasks. In our work, we propose a novel solution - the Progressive…

Incremental semantic segmentation(ISS) is an emerging task where old model is updated by incrementally adding new classes. At present, methods based on convolutional neural networks are dominant in ISS. However, studies have shown that such…

Catastrophic forgetting, the tendency of neural networks to forget previously learned knowledge when learning new tasks, has been a major challenge in continual learning (CL). To tackle this challenge, CL methods have been proposed and…

The two main challenges faced by continual learning approaches are catastrophic forgetting and memory limitations on the storage of data. To cope with these challenges, we propose a novel, cognitively-inspired approach which trains…