paper-with-me

홈 › Papers

Curriculum Learning by Dynamic Instance Hardness

2020-12-01 · NeurIPS 2020 12 · Tianyi Zhou, Shengjie Wang, Jeff A. Bilmes

A good teacher can adjust the curriculum based on students' learning history. By analogy, in this paper, we study the dynamics of a deep neural network's (DNN) performance on individual samples during its learning process. The observed properties allow us to develop an adaptive curriculum that leads to faster learning of more accurate models. We introduce dynamic instance hardness (DIH), the exponential moving average of a sample's instantaneous hardness (e.g., a loss, or a change in outputs) over the training history. A low DIH indicates that a model retains knowledge about a sample over time, and implies a flat loss landscape for that sample. Moreover, for DNNs, we find that a sample's DIH early in training predicts its DIH in later stages. Hence, we can train a model using samples with higher DIH and safely ignore those with lower DIH. This motivates a DIH guided curriculum learning (DIHCL). Compared to existing CL methods: (1) DIH is more stable over time than using only instantaneous hardness, which is noisy due to stochastic training and DNN's non-smoothness; (2) DIHCL is computationally inexpensive since it uses only a byproduct of back-propagation and thus does not require extra inference. On 11 datasets, DIHCL significantly outperforms random mini-batch SGD and recent CL methods in terms of efficiency and final performance.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Hardness-Aware Dynamic Curriculum Learning for Robust Multimodal Emotion Recognition with Missing Modalities

2025-08-09 · Rui Liu, Haolin Zuo, Zheng Lian, Hongyu Yuan 외 arxiv

Missing modalities have recently emerged as a critical research direction in multimodal emotion recognition (MER). Conventional approaches typically address this issue through missing modality reconstruction. However, th…

Multimodal Emotion Recognition

Dynamic Instance Hardness

2019-09-25 · Tianyi Zhou, Shengjie Wang, Jeff A. Bilmes

We introduce dynamic instance hardness (DIH) to facilitate the training of machine learning models. DIH is a property of each training sample and is computed as the running mean of the sample's instantaneous hardness as …

Towards General Deepfake Detection with Dynamic Curriculum

2024-10-15 · Wentang Song, Yuzhen Lin, Bin Li

Most previous deepfake detection methods bent their efforts to discriminate artifacts by end-to-end training. However, the learned networks often fail to mine the general face forgery information efficiently due to ignor…

DeepFake DetectionFace Swapping

Learning to Solve Travelling Salesman Problem with Hardness-adaptive Curriculum

2022-04-07 · Zeyang Zhang, Ziwei Zhang, Xin Wang, Wenwu Zhu

Various neural network models have been proposed to tackle combinatorial optimization problems such as the travelling salesman problem (TSP). Existing learning-based TSP methods adopt a simple setting that the training a…

Combinatorial Optimization

A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances

2021-10-03 · NeurIPS 2020 12 · Dieqiao Feng, Carla P. Gomes, Bart Selman

In recent years, we have witnessed tremendous progress in deep reinforcement learning (RL) for tasks such as Go, Chess, video games, and robot control. Nevertheless, other combinatorial domains, such as AI planning, stil…

Deep Reinforcement LearningReinforcement Learning (RL)Sokoban