Related papers: Prompt-augmented Temporal Point Process for Stream…
For continual learning, text-prompt-based methods leverage text encoders and learnable prompts to encode semantic features for sequentially arrived classes over time. A common challenge encountered by existing works is how to learn unique…
Attention guides our gaze to fixate the proper location of the scene and holds it in that location for the deserved amount of time given current processing demands, before shifting to the next one. As such, gaze deployment crucially is a…
Continual learning (CL) provides a framework for training models in ever-evolving environments. Although re-occurrence of previously seen objects or tasks is common in real-world problems, the concept of repetition in the data stream is not…
Lifelong event detection aims to incrementally update a model with new event types and data while retaining the capability on previously learned old types. One critical challenge is that the model would catastrophically forget old types…
We introduce Progressive Prompts - a simple and efficient approach for continual learning in language models. Our method allows forward transfer and resists catastrophic forgetting, without relying on data replay or a large number of…
Temporal point process as the stochastic process on continuous domain of time is commonly used to model the asynchronous event sequence featuring with occurrence timestamps. Thanks to the strong expressivity of deep neural networks, they…
Temporal point processes (TPPs) model the timing of discrete events along a timeline and are widely used in fields such as neuroscience and fi- nance. Statistical depth functions are powerful tools for analyzing centrality and ranking in…
A Marked Temporal Point Process (MTPP) is a stochastic process whose realization is a set of event-time data. MTPP is often used to understand complex dynamics of asynchronous temporal events such as money transaction, social media,…
Neural processes (NPs) learn stochastic processes and predict the distribution of target output adaptively conditioned on a context set of observed input-output pairs. Furthermore, Attentive Neural Process (ANP) improved the prediction…
Learning continuously during all model lifetime is fundamental to deploy machine learning solutions robust to drifts in the data distribution. Advances in Continual Learning (CL) with recurrent neural networks could pave the way to a large…
Recurrent Neural Networks (RNNs) have become the state-of-the-art choice for extracting patterns from temporal sequences. However, current RNN models are ill-suited to process irregularly sampled data triggered by events generated in…
Online discussion forum creates an asynchronous conversation environment for online users to exchange ideas and share opinions through a unique thread-reply communication mode. Accurately modeling information dynamics under such a mode is…
Electronic Health Records (EHR) can be represented as temporal sequences that record the events (medical visits) from patients. Neural temporal point process (NTPP) has achieved great success in modeling event sequences that occur in…
Social goods, such as healthcare, smart city, and information networks, often produce ordered event data in continuous time. The generative processes of these event data can be very complex, requiring flexible models to capture their…
Continuous-time event sequences, i.e., sequences consisting of continuous time stamps and associated event types ("marks"), are an important type of sequential data with many applications, e.g., in clinical medicine or user behavior…
The classical temporal point process (TPP) constructs an intensity function by taking the occurrence times into account. Nevertheless, occurrence time may not be the only relevant factor, other contextual data, termed covariates, may also…
Tracking entities throughout a procedure described in a text is challenging due to the dynamic nature of the world described in the process. Firstly, we propose to formulate this task as a question answering problem. This enables us to use…
Predicting irregularly spaced event sequences with discrete marks poses significant challenges due to the complex, asynchronous dependencies embedded within continuous-time data streams.Existing sequential approaches capture dependencies…
Today, massive amounts of streaming data from smart devices need to be analyzed automatically to realize the Internet of Things. The Complex Event Processing (CEP) paradigm promises low-latency pattern detection on event streams. However,…
Marked Temporal Point Processes (MTPPs) arise naturally in medical, social, commercial, and financial domains. However, existing Transformer-based methods mostly inject temporal information only via positional encodings, relying on shared…