Author name cluster

Pawan Goyal

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.

9 papers

1 author row

EAAI Journal 2025 Journal Article

A robust sparse identification of nonlinear dynamics approach by combining neural networks and an integral form

Ali Forootani
Pawan Goyal
Peter Benner

One widely used methodology for uncovering governing equations from data is sparse regression for nonlinear dynamics, commonly known as Sparse Identification of Nonlinear Dynamics (SINDy). However, noisy and limited data remain a significant challenge for the success of the SINDy approach. In this work, we propose a robust strategy to discover nonlinear governing equations from both noisy and scarce data. Specifically, we employ neural networks to learn an implicit representation from measurement data, thereby ensuring that the network output remains close to the measurements while also admitting a dynamical system interpretation for its time evolution. Moreover, we identify this dynamical system in the spirit of the SINDy framework. By leveraging the neural network’s implicit representation, we employ automatic differentiation to obtain the derivative information required by SINDy. To further enhance the robustness of our approach, we incorporate an integral constraint on the output of the implicit networks. In addition, we extend our method to handle data acquired from multiple initial conditions. Through several examples, we demonstrate the proposed method’s effectiveness in discovering governing equations under noisy, data-scarce conditions and compare its performance against existing methods.

Details DOI

NeurIPS Conference 2025 Conference Paper

LLM Meets Diffusion: A Hybrid Framework for Crystal Material Generation

Subhojyoti Khastagir
Kishalay Das
Pawan Goyal
Seung-Cheol Lee
Satadeep Bhattacharjee
Niloy Ganguly

Recent advances in generative modeling have shown significant promise in designing novel periodic crystal structures. Existing approaches typically rely on either large language models (LLMs) or equivariant denoising models, each with complementary strengths: LLMs excel at handling discrete atomic types but often struggle with continuous features such as atomic positions and lattice parameters, while denoising models are effective at modeling continuous variables but encounter difficulties in generating accurate atomic compositions. To bridge this gap, we propose CrysLLMGen, a hybrid framework that integrates an LLM with a diffusion model to leverage their complementary strengths for crystal material generation. During sampling, CrysLLMGen first employs a fine-tuned LLM to produce an intermediate representation of atom types, atomic coordinates, and lattice structure. While retaining the predicted atom types, it passes the atomic coordinates and lattice structure to a pre-trained equivariant diffusion model for refinement. Our framework outperforms state-of-the-art generative models across several benchmark tasks and datasets. Specifically, CrysLLMGen not only achieves a balanced performance in terms of structural and compositional validity but also generates more stable and novel materials compared to LLM-based and denoising-based models Furthermore, CrysLLMGen exhibits strong conditional generation capabilities, effectively producing materials that satisfy user-defined constraints. Code is available at \url{https: //github. com/kdmsit/crysllmgen}

PDF Details

TMLR Journal 2025 Journal Article

ReFeR: Improving Evaluation and Reasoning through Hierarchy of Models

Yaswanth Narsupalli
Abhranil Chandra
Sreevatsa Muppirala
Manish Gupta
Pawan Goyal

Assessing the quality of generative model outputs from large language models (LLMs) or vision-language models (VLMs), poses significant challenges. Traditional evaluation methods either rely on human assessment which is resource-intensive and not scalable or on automatic metrics that often correlate poorly with human preferences. Another approach is to train dedicated neural evaluators, but this typically requires substantial training data and compute. In this study, we thus introduce ReFeR, a tuning-free framework for evaluating generative outputs including both text and images, using a two-level hierarchy of pre-trained LLM and VLM evaluators. This multi-agent hierarchical strategy leverages additional compute at inference time by orchestrating multiple models and utilizing the increased test-time reasoning to boost performance. By having models themselves provide feedback and final judgments, ReFeR reduces the dependence on human evaluation. We rigorously evaluate ReFeR on four diverse evaluation benchmarks, where it surpasses prior methods in accuracy while also generating constructive feedback useful for downstream distillation and self-improvement via finetuning. Interestingly, ReFeR is also applicable for reasoning tasks - experiments on four reasoning benchmarks show ReFeR’s superior collective reasoning abilities. We present two variants of the framework: ReFeR-Turbo, optimized for accelerated performance, and ReFeR-Lite, offering a more test-time compute efficient solution. ReFeR-Lite is $\sim12-14\times$ more compute efficient than previous works while being comparably accurate to ReFeR-Turbo.

PDF Details

TMLR Journal 2024 Journal Article

FastDoc: Domain-Specific Fast Continual Pre-training Technique using Document-Level Metadata and Taxonomy

Abhilash Nandy
Manav Nitin Kapadnis
Sohan Patnaik
Yash Parag Butala
Pawan Goyal
Niloy Ganguly

In this paper, we propose FastDoc (Fast Continual Pre-training Technique using Document Level Metadata and Taxonomy), a novel, compute-efficient framework that utilizes Document metadata and Domain-Specific Taxonomy as supervision signals to continually pre-train transformer encoder on a domain-specific corpus. The main innovation is that during domain-specific pretraining, an open-domain encoder is continually pre-trained using sentence-level embeddings as inputs (to accommodate long documents), however, fine-tuning is done with token-level embeddings as inputs to this encoder. We perform such domain-specific pre-training on three different domains namely customer support, scientific, and legal domains, and compare performance on 6 different downstream tasks and 9 different datasets. The novel use of document-level supervision along with sentence-level embedding input for pre-training reduces pre-training compute by around 1,000, 4,500, and 500 times compared to MLM and/or NSP in Customer Support, Scientific, and Legal Domains, respectively. The reduced training time does not lead to a deterioration in performance. In fact we show that FastDoc either outperforms or performs on par with several competitive transformer-based baselines in terms of character-level F1 scores and other automated metrics in the Customer Support, Scientific, and Legal Domains. Moreover, reduced training aids in mitigating the risk of catastrophic forgetting. Thus, unlike baselines, FastDoc shows a negligible drop in performance on open domain.

PDF Details

AAAI Conference 2023 Conference Paper

CrysGNN: Distilling Pre-trained Knowledge to Enhance Property Prediction for Crystalline Materials

Kishalay Das
Bidisha Samanta
Pawan Goyal
Seung-Cheol Lee
Satadeep Bhattacharjee
Niloy Ganguly

In recent years, graph neural network (GNN) based approaches have emerged as a powerful technique to encode complex topological structure of crystal materials in an enriched repre- sentation space. These models are often supervised in nature and using the property-specific training data, learn relation- ship between crystal structure and different properties like formation energy, bandgap, bulk modulus, etc. Most of these methods require a huge amount of property-tagged data to train the system which may not be available for different prop- erties. However, there is an availability of a huge amount of crystal data with its chemical composition and structural bonds. To leverage these untapped data, this paper presents CrysGNN, a new pre-trained GNN framework for crystalline materials, which captures both node and graph level structural information of crystal graphs using a huge amount of unla- belled material data. Further, we extract distilled knowledge from CrysGNN and inject into different state of the art prop- erty predictors to enhance their property prediction accuracy. We conduct extensive experiments to show that with distilled knowledge from the pre-trained model, all the SOTA algo- rithms are able to outperform their own vanilla version with good margins. We also observe that the distillation process provides significant improvement over the conventional ap- proach of finetuning the pre-trained model. We will release the pre-trained model along with the large dataset of 800K crys- tal graph which we carefully curated; so that the pre-trained model can be plugged into any existing and upcoming models to enhance their prediction accuracy.

PDF Details DOI

AAAI Conference 2022 Conference Paper

LeSICiN: A Heterogeneous Graph-Based Approach for Automatic Legal Statute Identification from Indian Legal Documents

Shounak Paul
Pawan Goyal
Saptarshi Ghosh

The task of Legal Statute Identification (LSI) aims to identify the legal statutes that are relevant to a given description of facts or evidence of a legal case. Existing methods only utilize the textual content of facts and legal articles to guide such a task. However, the citation network among case documents and legal statutes is a rich source of additional information, which is not considered by existing models. In this work, we take the first step towards utilising both the text and the legal citation network for the LSI task. We curate a large novel dataset for this task, including facts of cases from several major Indian Courts of Law, and statutes from the Indian Penal Code (IPC). Modeling the statutes and training documents as a heterogeneous graph, our proposed model LeSICiN can learn rich textual and graphical features, and can also tune itself to correlate these features. Thereafter, the model can be used to inductively predict links between test documents (new nodes whose graphical features are not available to the model) and statutes (existing nodes). Extensive experiments on the dataset show that our model comfortably outperforms several state-of-the-art baselines, by exploiting the graphical structure along with textual features.

PDF Details

AAAI Conference 2021 Conference Paper

HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection

Binny Mathew
Punyajoy Saha
Seid Muhie Yimam
Chris Biemann
Pawan Goyal
Animesh Mukherjee

Hate speech is a challenging issue plaguing the online social media. While better models for hate speech detection are continuously being developed, there is little research on the bias and interpretability aspects of hate speech. In this paper, we introduce HateXplain, the first benchmark hate speech dataset covering multiple aspects of the issue. Each post in our dataset is annotated from three different perspectives: the basic, commonly used 3-class classification (i. e. , hate, offensive or normal), the target community (i. e. , the community that has been the victim of hate speech/offensive speech in the post), and the rationales, i. e. , the portions of the post on which their labelling decision (as hate, offensive or normal) is based. We utilize existing state-of-the-art models and observe that even models that perform very well in classification do not score high on explainability metrics like model plausibility and faithfulness. We also observe that models, which utilize the human rationales for training, perform better in reducing unintended bias towards target communities. We have made our code and dataset public1 for other researchers2.

PDF Details

IJCAI Conference 2020 Conference Paper

Logic Constrained Pointer Networks for Interpretable Textual Similarity

Subhadeep Maji
Rohan Kumar
Manish Bansal
Kalyani Roy
Pawan Goyal

Systematically discovering semantic relationships in text is an important and extensively studied area in Natural Language Processing, with various tasks such as entailment, semantic similarity, etc. Decomposability of sentence-level scores via subsequence alignments has been proposed as a way to make models more interpretable. We study the problem of aligning components of sentences leading to an interpretable model for semantic textual similarity. In this paper, we introduce a novel pointer network based model with a sentinel gating function to align constituent chunks, which are represented using BERT. We improve this base model with a loss function to equally penalize misalignments in both sentences, ensuring the alignments are bidirectional. Finally, to guide the network with structured external knowledge, we introduce first-order logic constraints based on ConceptNet and syntactic knowledge. The model achieves an F1 score of 97. 73 and 96. 32 on the benchmark SemEval datasets for the chunk alignment task, showing large improvements over the existing solutions. Source code is available at https: //github. com/manishb89/interpretable_sentence_similarity

PDF Details DOI

TAAS Journal 2008 Journal Article

Agile dynamic provisioning of multi-tier Internet applications

Bhuvan Urgaonkar
Prashant Shenoy
Abhishek Chandra
Pawan Goyal
Timothy Wood

Dynamic capacity provisioning is a useful technique for handling the multi-time-scale variations seen in Internet workloads. In this article, we propose a novel dynamic provisioning technique for multi-tier Internet applications that employs (1) a flexible queuing model to determine how much of the resources to allocate to each tier of the application, and (2) a combination of predictive and reactive methods that determine when to provision these resources, both at large and small time scales. We propose a novel data center architecture based on virtual machine monitors to reduce provisioning overheads. Our experiments on a forty-machine Xen/Linux-based hosting platform demonstrate the responsiveness of our technique in handling dynamic workloads. In one scenario where a flash crowd caused the workload of a three-tier application to double, our technique was able to double the application capacity within five minutes, thus maintaining response-time targets. Our technique also reduced the overhead of switching servers across applications from several minutes to less than a second, while meeting the performance targets of residual sessions.

Details DOI