Author name cluster

Rahul Vigneswaran

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.

3 papers

1 author row

TMLR Journal 2026 Journal Article

Transitioning Heads Conundrum: The Hidden Bottleneck in Long-Tailed Class-Incremental Learning

Rahul Vigneswaran
Hari Chandana Kuchibhotla
Vineeth N. Balasubramanian

Long-Tailed Class-Incremental Learning (LTCIL) faces a fundamental tension: models must sequentially learn new classes while contending with extreme class imbalance, which amplifies catastrophic forgetting. A particularly overlooked phenomenon is the Transitioning Heads Conundrum: as replay buffers constrain memory, initially well-represented head classes shrink over time and effectively become tail classes, undermining knowledge retention. Existing approaches fail to address this because they apply knowledge distillation too late, after these transitions have already eroded head-class representations. To overcome this, we introduce DEcoupling Representations for Early Knowledge distillation (DEREK), which strategically employs Early Knowledge Distillation to safeguard head-class knowledge before data constraints manifest. Comprehensive evaluation across 2 LTCIL benchmarks, 12 experimental settings, and 24 baselines, including Long-Tail, Class-Incremental, Few-Shot CIL, and LTCIL methods, shows that DEREK maintains competitive performance across categories, establishing new state-of-the-art results.

PDF Details

TMLR Journal 2025 Journal Article

HARE: Human-in-the-Loop Algorithmic Recourse

Sai Srinivas Kancheti
Rahul Vigneswaran
Bamdev Mishra
Vineeth N. Balasubramanian

Machine learning models are seeing increasing use as decision making systems in domains such as education, finance and healthcare. It is desirable that these models are trustworthy to the end-user, by ensuring fairness, transparency and reliability of decisions. In this work, we consider a key aspect of responsible and transparent AI models -- actionable explanations, viz. the ability of such models to provide recourse to end users adversely affected by their decisions. While algorithmic recourse has seen a variety of efforts in recent years, there have been very few efforts on exploring personalized recourse for a given user. Two users with the same feature profile may prefer vastly different recourses. The limited work in this direction hitherto rely on one-time feature preferences provided by a user. Instead, we present a human-in-the-loop formulation of algorithmic recourse that can incorporate both relative and absolute human feedback for a given test instance. We show that our formulation can extend any existing recourse generating method, enabling the generation of recourses that are satisfactory to the user. We perform experiments on 3 benchmark datasets on top of 6 popular baseline recourse methods where we observe that our framework performs significantly better on simulated user preferences.

PDF Details

AAAI Conference 2021 Conference Paper

A Deeper Look at the Hessian Eigenspectrum of Deep Neural Networks and its Applications to Regularization

Adepu Ravi Sankar
Yash Khasbage
Rahul Vigneswaran
Vineeth N Balasubramanian

Loss landscape analysis is extremely useful for a deeper understanding of the generalization ability of deep neural network models. In this work, we propose a layerwise loss landscape analysis where the loss surface at every layer is studied independently and also on how each correlates to the overall loss surface. We study the layerwise loss landscape by studying the eigenspectra of the Hessian at each layer. In particular, our results show that the layerwise Hessian geometry is largely similar to the entire Hessian. We also report an interesting phenomenon where the Hessian eigenspectrum of middle layers of the deep neural network are observed to most similar to the overall Hessian eigenspectrum. We also show that the maximum eigenvalue and the trace of the Hessian (both full network and layerwise) reduce as training of the network progresses. We leverage on these observations to propose a new regularizer based on the trace of the layerwise Hessian. Penalizing the trace of the Hessian at every layer indirectly forces Stochastic Gradient Descent to converge to flatter minima, which are shown to have better generalization performance. In particular, we show that such a layerwise regularizer can be leveraged to penalize the middlemost layers alone, which yields promising results. Our empirical studies on well-known deep nets across datasets support the claims of this work.

PDF Details