activity
20232025
most citedCompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competition

1 citations · 3 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2025

PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning

M. Anwar Ma'sum, Mahardhika Pratama, Savitha Ramasamy +3

The data privacy constraint in online continual learning (OCL), where the data can be seen only once, complicates the catastrophic forgetting problem in streaming data. A common ap…

cs.LG2025

Multi-Scale Finetuning for Encoder-based Time Series Foundation Models

Zhongzheng Qiao, Chenghao Liu, Yiming Zhang +6

Time series foundation models (TSFMs) demonstrate impressive zero-shot performance for time series forecasting. However, an important yet underexplored challenge is how to effectiv…

cs.LG2025

Sequence Transferability and Task Order Selection in Continual Learning

Thinh Nguyen, Cuong N. Nguyen, Quang Pham +4

In continual learning, understanding the properties of task sequences and their relationships to model performance is important for developing advanced algorithms with better accur…

cs.LG2024★ 1 cited

PIP: Prototypes-Injected Prompt for Federated Class Incremental Learning

Muhammad Anwar Ma'sum, Mahardhika Pratama, Savitha Ramasamy +3

Federated Class Incremental Learning (FCIL) is a new direction in continual learning (CL) for addressing catastrophic forgetting and non-IID data distribution simultaneously. Exist…

cs.LG2024★ 1 cited

CompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competition

Quang Pham, Giang Do, Huy Nguyen +8

Sparse mixture of experts (SMoE) offers an appealing solution to scale up the model complexity beyond the mean of increasing the network's depth or width. However, effective traini…

cs.LG2024★ 1 cited

Class-incremental Learning for Time Series: Benchmark and Evaluation

Zhongzheng Qiao, Quang Pham, Zhen Cao +4

Real-world environments are inherently non-stationary, frequently introducing new classes over time. This is especially common in time series classification, such as the emergence…