Author name cluster

Fahad Sarfraz

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

2 author rows

TMLR Journal 2025 Journal Article

Consistency Aware Robust Learning under Noisy Labels

Fahad Sarfraz
Bahram Zonooz
Elahe Arani

Deep neural networks (DNNs) often struggle with noisy supervision, a common challenge in real-world datasets where high-quality annotations are scarce. While DNNs tend to memorize noisy labels, the human brain excels at learning in noisy environments by modulating sensitivity to errors based on their magnitude and consistency. Inspired by this, we propose Consistency-Aware Robust Learning (CARoL), which maintains a memory of past predictions and errors to quantify consistency and guide the learning process. CARoL employs a principled mechanism to distinguish clean from noisy samples and modulates rate of adaptation based on prediction consistency. Furthermore, it integrates multiple learning pathways to fully utilize the dataset, adapting to sample characteristics as training progresses. Our empirical evaluation shows that CARoL achieves high precision in noisy label detection, enhances robustness, and performs reliably under severe noise, highlighting the potential of biologically inspired approaches for robust learning.

PDF Details

ICLR Conference 2025 Conference Paper

Semantic Aware Representation Learning for Lifelong Learning

Fahad Sarfraz
Elahe Arani
Bahram Zonooz

The human brain excels at lifelong learning by not only encoding information in sparse activation codes but also leveraging rich semantic structures and relationships between newly encountered and previously learned objects. This ability to utilize semantic similarities is crucial for efficient learning and knowledge consolidation, yet is often underutilized in current continual learning approaches. To bridge this gap, we propose Semantic-Aware Representation Learning (SARL) which employs sparse activations and a principled approach to evaluate similarities between objects encountered across different tasks and subsequently uses them to guide representation learning. Using these relationships, SARL enhances the reusability of features and reduces interference between tasks. This approach empowers the model to adapt to new information while maintaining stability, significantly improving performance in complex incremental learning scenarios. Our analysis demonstrates that SARL achieves a superior balance between plasticity and stability by harnessing the underlying semantic structure.

Details

TMLR Journal 2023 Journal Article

A Study of Biologically Plausible Neural Network: The Role and Interactions of Brain-Inspired Mechanisms in Continual Learning

Fahad Sarfraz
Elahe Arani
Bahram Zonooz

Humans excel at continually acquiring, consolidating, and retaining information from an ever-changing environment, whereas artificial neural networks (ANNs) exhibit catastrophic forgetting. There are considerable differences in the complexity of synapses, the processing of information, and the learning mechanisms in biological neural networks and their artificial counterparts, which may explain the mismatch in performance. We consider a biologically plausible framework that constitutes separate populations of exclusively excitatory and inhibitory neurons that adhere to Dale's principle, and the excitatory pyramidal neurons are augmented with dendritic-like structures for context-dependent processing of stimuli. We then conduct a comprehensive study on the role and interactions of different mechanisms inspired by the brain, including sparse non-overlapping representations, Hebbian learning, synaptic consolidation, and replay of past activations that accompanied the learning event. Our study suggests that the employing of multiple complementary mechanisms in a biologically plausible architecture, similar to the brain, may be effective in enabling continual learning in ANNs. \footnote{We will make the code available upon acceptance.

PDF Details

ICLR Conference 2023 Conference Paper

Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning

Fahad Sarfraz
Elahe Arani
Bahram Zonooz

Humans excel at lifelong learning, as the brain has evolved to be robust to distribution shifts and noise in our ever-changing environment. Deep neural networks (DNNs), however, exhibit catastrophic forgetting and the learned representations drift drastically as they encounter a new task. This alludes to a different error-based learning mechanism in the brain. Unlike DNNs, where learning scales linearly with the magnitude of the error, the sensitivity to errors in the brain decreases as a function of their magnitude. To this end, we propose "ESMER" which employs a principled mechanism to modulate error sensitivity in a dual-memory rehearsal-based system. Concretely, it maintains a memory of past errors and uses it to modify the learning dynamics so that the model learns more from small consistent errors compared to large sudden errors. We also propose "Error-Sensitive Reservoir Sampling" to maintain episodic memory, which leverages the error history to pre-select low-loss samples as candidates for the buffer, which are better suited for retaining information. Empirical results show that ESMER effectively reduces forgetting and abrupt drift in representations at the task boundary by gradually adapting to the new task while consolidating knowledge. Remarkably, it also enables the model to learn under high levels of label noise, which is ubiquitous in real-world data streams.

Details

AAAI Conference 2023 Conference Paper

Sparse Coding in a Dual Memory System for Lifelong Learning

Fahad Sarfraz
Elahe Arani
Bahram Zonooz

Efficient continual learning in humans is enabled by a rich set of neurophysiological mechanisms and interactions between multiple memory systems. The brain efficiently encodes information in non-overlapping sparse codes, which facilitates the learning of new associations faster with controlled interference with previous associations. To mimic sparse coding in DNNs, we enforce activation sparsity along with a dropout mechanism which encourages the model to activate similar units for semantically similar inputs and have less overlap with activation patterns of semantically dissimilar inputs. This provides us with an efficient mechanism for balancing the reusability and interference of features, depending on the similarity of classes across tasks. Furthermore, we employ sparse coding in a multiple-memory replay mechanism. Our method maintains an additional long-term semantic memory that aggregates and consolidates information encoded in the synaptic weights of the working model. Our extensive evaluation and characteristics analysis show that equipped with these biologically inspired mechanisms, the model can further mitigate forgetting. Code available at \url{https://github.com/NeurAI-Lab/SCoMMER}.

PDF Details DOI

ICLR Conference 2022 Conference Paper

Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System

Elahe Arani
Fahad Sarfraz
Bahram Zonooz

Humans excel at continually learning from an ever-changing environment whereas it remains a challenge for deep neural networks which exhibit catastrophic forgetting. The complementary learning system (CLS) theory suggests that the interplay between rapid instance-based learning and slow structured learning in the brain is crucial for accumulating and retaining knowledge. Here, we propose CLS-ER, a novel dual memory experience replay (ER) method which maintains short-term and long-term semantic memories that interact with the episodic memory. Our method employs an effective replay mechanism whereby new knowledge is acquired while aligning the decision boundaries with the semantic memories. CLS-ER does not utilize the task boundaries or make any assumption about the distribution of the data which makes it versatile and suited for ``general continual learning''. Our approach achieves state-of-the-art performance on standard benchmarks as well as more realistic general continual learning settings.

Details