Gobinda Saha

Utkarsh Saxena, Gobinda Saha, Sakshi Choudhary et al.

Large language models (LLMs) represent a groundbreaking advancement in the domain of natural language processing due to their impressive reasoning abilities. Recently, there has been considerable interest in increasing the context lengths for these models to enhance their applicability to complex tasks. However, at long context lengths and large batch sizes, the key-value (KV) cache, which stores the attention keys and values, emerges as the new bottleneck in memory usage during inference. To address this, we propose Eigen Attention, which performs the attention operation in a low-rank space, thereby reducing the KV cache memory overhead. Our proposed approach is orthogonal to existing KV cache compression techniques and can be used synergistically with them. Through extensive experiments over OPT, MPT, and Llama model families, we demonstrate that Eigen Attention results in up to 40% reduction in KV cache sizes and up to 60% reduction in attention operation latency with minimal drop in performance. Code is available at https://github.com/UtkarshSaxena1/EigenAttn.

Gobinda Saha, Kaushik Roy

In neural networks, continual learning results in gradient interference among sequential tasks, leading to catastrophic forgetting of old tasks while learning new ones. This issue is addressed in recent methods by storing the important gradient spaces for old tasks and updating the model orthogonally during new tasks. However, such restrictive orthogonal gradient updates hamper the learning capability of the new tasks resulting in sub-optimal performance. To improve new learning while minimizing forgetting, in this paper we propose a Scaled Gradient Projection (SGP) method, where we combine the orthogonal gradient projections with scaled gradient steps along the important gradient spaces for the past tasks. The degree of gradient scaling along these spaces depends on the importance of the bases spanning them. We propose an efficient method for computing and accumulating importance of these bases using the singular value decomposition of the input representations for each task. We conduct extensive experiments ranging from continual image classification to reinforcement learning tasks and report better performance with less training overhead than the state-of-the-art approaches.

Deepak Ravikumar, Gobinda Saha, Sai Aparna Aketi et al.

Decentralized learning enables serverless training of deep neural networks (DNNs) in a distributed manner on multiple nodes. This allows for the use of large datasets, as well as the ability to train with a wide variety of data sources. However, one of the key challenges with decentralized learning is heterogeneity in the data distribution across the nodes. In this paper, we propose In-Distribution Knowledge Distillation (IDKD) to address the challenge of heterogeneous data distribution. The goal of IDKD is to homogenize the data distribution across the nodes. While such data homogenization can be achieved by exchanging data among the nodes sacrificing privacy, IDKD achieves the same objective using a common public dataset across nodes without breaking the privacy constraint. This public dataset is different from the training dataset and is used to distill the knowledge from each node and communicate it to its neighbors through the generated labels. With traditional knowledge distillation, the generalization of the distilled model is reduced because all the public dataset samples are used irrespective of their similarity to the local dataset. Thus, we introduce an Out-of-Distribution (OoD) detector at each node to label a subset of the public dataset that maps close to the local training data distribution. Finally, only labels corresponding to these subsets are exchanged among the nodes and with appropriate label averaging each node is finetuned on these data subsets along with its local data. Our experiments on multiple image classification datasets and graph topologies show that the proposed IDKD scheme is more effective than traditional knowledge distillation and achieves state-of-the-art generalization performance on heterogeneously distributed data with minimal communication overhead.

Sakshi Choudhary, Sai Aparna Aketi, Gobinda Saha et al.

Training at the edge utilizes continuously evolving data generated at different locations. Privacy concerns prohibit the co-location of this spatially as well as temporally distributed data, deeming it crucial to design training algorithms that enable efficient continual learning over decentralized private data. Decentralized learning allows serverless training with spatially distributed data. A fundamental barrier in such distributed learning is the high bandwidth cost of communicating model updates between agents. Moreover, existing works under this training paradigm are not inherently suitable for learning a temporal sequence of tasks while retaining the previously acquired knowledge. In this work, we propose CoDeC, a novel communication-efficient decentralized continual learning algorithm which addresses these challenges. We mitigate catastrophic forgetting while learning a task sequence in a decentralized learning setup by combining orthogonal gradient projection with gossip averaging across decentralized agents. Further, CoDeC includes a novel lossless communication compression scheme based on the gradient subspaces. We express layer-wise gradients as a linear combination of the basis vectors of these gradient subspaces and communicate the associated coefficients. We theoretically analyze the convergence rate for our algorithm and demonstrate through an extensive set of experiments that CoDeC successfully learns distributed continual tasks with minimal forgetting. The proposed compression scheme results in up to 4.8x reduction in communication costs with iso-performance as the full communication baseline.

Efstathia Soufleri, Gobinda Saha, Kaushik Roy

Machine Learning (ML) has achieved enormous success in solving a variety of problems in computer vision, speech recognition, object detection, to name a few. The principal reason for this success is the availability of huge datasets for training deep neural networks (DNNs). However, datasets can not be publicly released if they contain sensitive information such as medical or financial records. In such cases, data privacy becomes a major concern. Encryption methods offer a possible solution to this issue, however their deployment on ML applications is non-trivial, as they seriously impact the classification accuracy and result in substantial computational overhead.Alternatively, obfuscation techniques can be used, but maintaining a good balance between visual privacy and accuracy is challenging. In this work, we propose a method to generate secure synthetic datasets from the original private datasets. In our method, given a network with Batch Normalization (BN) layers pre-trained on the original dataset, we first record the layer-wise BN statistics. Next, using the BN statistics and the pre-trained model, we generate the synthetic dataset by optimizing random noises such that the synthetic data match the layer-wise statistical distribution of the original model. We evaluate our method on image classification dataset (CIFAR10) and show that our synthetic data can be used for training networks from scratch, producing reasonable classification performance.

Sangamesh Kodge, Deepak Ravikumar, Gobinda Saha et al.

Label corruption, where training samples are mislabeled due to non-expert annotation or adversarial attacks, significantly degrades model performance. Acquiring large, perfectly labeled datasets is costly, and retraining models from scratch is computationally expensive. To address this, we introduce Scaled Activation Projection (SAP), a novel SVD (Singular Value Decomposition)-based corrective machine unlearning algorithm. SAP mitigates label noise by identifying a small subset of trusted samples using cross-entropy loss and projecting model weights onto a clean activation space estimated using SVD on these trusted samples. This process suppresses the noise introduced in activations due to the mislabeled samples. In our experiments, we demonstrate SAP's effectiveness on synthetic noise with different settings and real-world label noise. SAP applied to the CIFAR dataset with 25% synthetic corruption show upto 6% generalization improvements. Additionally, SAP can improve the generalization over noise robust training approaches on CIFAR dataset by ~3.2% on average. Further, we observe generalization improvements of 2.31% for a Vision Transformer model trained on naturally corrupted Clothing1M.

Gobinda Saha, Kaushik Roy

Artificial learning systems aspire to mimic human intelligence by continually learning from a stream of tasks without forgetting past knowledge. One way to enable such learning is to store past experiences in the form of input examples in episodic memory and replay them when learning new tasks. However, performance of such method suffers as the size of the memory becomes smaller. In this paper, we propose a new approach for experience replay, where we select the past experiences by looking at the saliency maps which provide visual explanations for the model's decision. Guided by these saliency maps, we pack the memory with only the parts or patches of the input images important for the model's prediction. While learning a new task, we replay these memory patches with appropriate zero-padding to remind the model about its past decisions. We evaluate our algorithm on CIFAR-100, miniImageNet and CUB datasets and report better performance than the state-of-the-art approaches. With qualitative and quantitative analyses we show that our method captures richer summaries of past experiences without any memory increase, and hence performs well with small episodic memory.

Gobinda Saha, Isha Garg, Kaushik Roy

The ability to learn continually without forgetting the past tasks is a desired attribute for artificial learning systems. Existing approaches to enable such learning in artificial neural networks usually rely on network growth, importance based weight update or replay of old data from the memory. In contrast, we propose a novel approach where a neural network learns new tasks by taking gradient steps in the orthogonal direction to the gradient subspaces deemed important for the past tasks. We find the bases of these subspaces by analyzing network representations (activations) after learning each task with Singular Value Decomposition (SVD) in a single shot manner and store them in the memory as Gradient Projection Memory (GPM). With qualitative and quantitative analyses, we show that such orthogonal gradient descent induces minimum to no interference with the past tasks, thereby mitigates forgetting. We evaluate our algorithm on diverse image classification datasets with short and long sequences of tasks and report better or on-par performance compared to the state-of-the-art approaches.

Gobinda Saha, Isha Garg, Aayush Ankit et al.

Humans learn adaptively and efficiently throughout their lives. However, incrementally learning tasks causes artificial neural networks to overwrite relevant information learned about older tasks, resulting in 'Catastrophic Forgetting'. Efforts to overcome this phenomenon often utilize resources poorly, for instance, by growing the network architecture or needing to save parametric importance scores, or violate data privacy between tasks. To tackle this, we propose SPACE, an algorithm that enables a network to learn continually and efficiently by partitioning the learnt space into a Core space, that serves as the condensed knowledge base over previously learned tasks, and a Residual space, which is akin to a scratch space for learning the current task. After learning each task, the Residual is analyzed for redundancy, both within itself and with the learnt Core space. A minimal number of extra dimensions required to explain the current task are added to the Core space and the remaining Residual is freed up for learning the next task. We evaluate our algorithm on P-MNIST, CIFAR and a sequence of 8 different datasets, and achieve comparable accuracy to the state-of-the-art methods while overcoming catastrophic forgetting. Additionally, our algorithm is well suited for practical use. The partitioning algorithm analyzes all layers in one shot, ensuring scalability to deeper networks. Moreover, the analysis of dimensions translates to filter-level sparsity, and the structured nature of the resulting architecture gives us up to 5x improvement in energy efficiency during task inference over the current state-of-the-art.