arXiv subjects

Navdeep Kaur

Publications and source records attributed to Navdeep Kaur.

15 recordsLinked to original sources

arXiv2025

DecompSR: A dataset for decomposed analyses of compositional multihop spatial reasoning

We introduce DecompSR, decomposed spatial reasoning, a large benchmark dataset (over 5m datapoints) and generation framework designed to analyse compositional spatial reasoning ability. The generation of DecompSR allows users to independently vary several aspects of compositionality, namely: productivity (reasoning depth), substitutivity (entity and linguistic variability), overgeneralisation (input order, distractors) and systematicity (novel linguistic elements). DecompSR is built procedurally in a manner which makes it is correct by construction, which is independently verified using a symbolic solver to guarantee the correctness of the dataset. DecompSR is comprehensively benchmarked across a host of Large Language Models (LLMs) where we show that LLMs struggle with productive and systematic generalisation in spatial reasoning tasks whereas they are more robust to linguistic variation. DecompSR provides a provably correct and rigorous benchmarking dataset with a novel ability to independently vary the degrees of several key aspects of compositionality, allowing for robust and fine-grained probing of the compositional reasoning abilities of LLMs.

cs.AI↗

arXiv2025

An Empirical Study of Conformal Prediction in LLM with ASP Scaffolds for Robust Reasoning

In this paper, we examine the use of Conformal Language Modelling (CLM) alongside Answer Set Programming (ASP) to enhance the performance of standard open-weight LLMs on complex multi-step reasoning tasks. Using the StepGame dataset, which requires spatial reasoning, we apply CLM to generate sets of ASP programs from an LLM, providing statistical guarantees on the correctness of the outputs. Experimental results show that CLM significantly outperforms baseline models that use standard sampling methods, achieving substantial accuracy improvements across different levels of reasoning complexity. Additionally, the LLM-as-Judge metric enhances CLM's performance, especially in assessing structurally and logically correct ASP outputs. However, calibrating CLM with diverse calibration sets did not improve generalizability for tasks requiring much longer reasoning steps, indicating limitations in handling more complex tasks.

cs.CL↗

arXiv2024

Simple Augmentations of Logical Rules for Neuro-Symbolic Knowledge Graph Completion

High-quality and high-coverage rule sets are imperative to the success of Neuro-Symbolic Knowledge Graph Completion (NS-KGC) models, because they form the basis of all symbolic inferences. Recent literature builds neural models for generating rule sets, however, preliminary experiments show that they struggle with maintaining high coverage. In this work, we suggest three simple augmentations to existing rule sets: (1) transforming rules to their abductive forms, (2) generating equivalent rules that use inverse forms of constituent relations and (3) random walks that propose new rules. Finally, we prune potentially low quality rules. Experiments over four datasets and five ruleset-baseline settings suggest that these simple augmentations consistently improve results, and obtain up to 7.1 pt MRR and 8.5 pt Hits@1 gains over using rules without augmentations.

cs.AI↗

arXiv2023

DynaSemble: Dynamic Ensembling of Textual and Structure-Based Models for Knowledge Graph Completion

We consider two popular approaches to Knowledge Graph Completion (KGC): textual models that rely on textual entity descriptions, and structure-based models that exploit the connectivity structure of the Knowledge Graph (KG). Preliminary experiments show that these approaches have complementary strengths: structure-based models perform exceptionally well when the gold answer is easily reachable from the query head in the KG, while textual models exploit descriptions to give good performance even when the gold answer is not easily reachable. In response, we propose DynaSemble, a novel method for learning query-dependent ensemble weights to combine these approaches by using the distributions of scores assigned by the models in the ensemble to all candidate entities. DynaSemble achieves state-of-the-art results on three standard KGC datasets, with up to 6.8 pt MRR and 8.3 pt Hits@1 gains over the best baseline model for the WN18RR dataset.

cs.CL↗

arXiv2023

NeuSTIP: A Novel Neuro-Symbolic Model for Link and Time Prediction in Temporal Knowledge Graphs

While Knowledge Graph Completion (KGC) on static facts is a matured field, Temporal Knowledge Graph Completion (TKGC), that incorporates validity time into static facts is still in its nascent stage. The KGC methods fall into multiple categories including embedding-based, rule-based, GNN-based, pretrained Language Model based approaches. However, such dimensions have not been explored in TKG. To that end, we propose a novel temporal neuro-symbolic model, NeuSTIP, that performs link prediction and time interval prediction in a TKG. NeuSTIP learns temporal rules in the presence of the Allen predicates that ensure the temporal consistency between neighboring predicates in a given rule. We further design a unique scoring function that evaluates the confidence of the candidate answers while performing link prediction and time interval prediction by utilizing the learned rules. Our empirical evaluation on two time interval based TKGC datasets suggests that our model outperforms state-of-the-art models for both link prediction and the time interval prediction task.

cs.AI↗

arXiv2020

Knowledge Graph Alignment using String Edit Distance

In this work, we propose a novel knowledge graph alignment technique based upon string edit distance that exploits the type information between entities and can find similarity between relations of any arity

cs.AI↗

arXiv2020

Non-Parametric Learning of Lifted Restricted Boltzmann Machines

We consider the problem of discriminatively learning restricted Boltzmann machines in the presence of relational data. Unlike previous approaches that employ a rule learner (for structure learning) and a weight learner (for parameter learning) sequentially, we develop a gradient-boosted approach that performs both simultaneously. Our approach learns a set of weak relational regression trees, whose paths from root to leaf are conjunctive clauses and represent the structure, and whose leaf values represent the parameters. When the learned relational regression trees are transformed into a lifted RBM, its hidden nodes are precisely the conjunctive clauses derived from the relational regression trees. This leads to a more interpretable and explainable model. Our empirical evaluations clearly demonstrate this aspect, while displaying no loss in effectiveness of the learned models.

cs.LG↗

arXiv2019

Quark Wigner Distributions and GTMDs of Pion in the Light-Front Holographic Model

We investigate the quark Wigner distributions of the pion to reveal the multidimensional picture of pion. We have used the spin improved wave functions of pion deduced from the light-front holographic model of mesons. By using the Fock-state overlap representation, the Wigner distributions of an unpolarized, longitudinally polarized and transversely polarized quark inside the pion are calculated. We have presented the results of transverse Wigner distributions in impact-parameter space as well as in momentum space. In order to understand the role of skewness which gives the longitudinal momentum transfer between the quarks, we study the six-dimensional phase-space distribution: the generalized transverse momentum dependent parton distributions of pion for the case of zero skewness as well as for nonzero value of skewness.

hep-ph↗

arXiv2019

Neural Networks for Relational Data

While deep networks have been enormously successful over the last decade, they rely on flat-feature vector representations, which makes them unsuitable for richly structured domains such as those arising in applications like social network analysis. Such domains rely on relational representations to capture complex relationships between entities and their attributes. Thus, we consider the problem of learning neural networks for relational data. We distinguish ourselves from current approaches that rely on expert hand-coded rules by learning relational random-walk-based features to capture local structural interactions and the resulting network architecture. We further exploit parameter tying of the network weights of the resulting relational neural network, where instances of the same type share parameters. Our experimental results across several standard relational data sets demonstrate the effectiveness of the proposed approach over multiple neural net baselines as well as state-of-the-art statistical relational models.

cs.LG↗

arXiv2019

Transverse momentum dependent parton distributions of pion in the light-front holographic model

Using the light-front holographic model, we study the transverse momentum dependent parton distributions (TMDs) for the case of pion. At leading twist, the unpolarized parton distribution function $ f_{1\pi}(x,\bfk^{2}) $ and the Boer-Mulders function $ h_{1\pi}^{\bot}(x,\bfk^{2}) $ are obtained for pion. We calculate both the functions using the light-front holographic model with spin improved wave function and compare the predicted results with available results of other models. In order to provide inputs in predicting future experimental data, a LO evolution is performed from model scale to experimental scale for the case of unpolarized parton distribution function $ f_{1\pi}(x,\bfk^{2}) $.

hep-ph↗

arXiv2018

Generalized Parton Distributions of Pion for Non-Zero Skewness in AdS/QCD

We study the generalized parton distributions (GPDs) of pion for non-zero skewness by considering the leading $| q \bar{q} \rangle$ Fock state component. Inspired from AdS/QCD light-front wave functions, we calculate the pion GPDs. By taking the Fourier transforms we obtain the results for impact-parameter dependent parton distribution functions (ipdpdf) and for GPDs in longitudinal boost-invariant space. We also calculate the charge density and gravitational form factor of the pion. The pion unpolarized transverse momentum distribution (TMD) have also been calculated. The results provide rich information on the internal structure of pion.

hep-ph↗

arXiv2018

Transverse momentum distributions of electron in simulated QED model

In the present work, we have studied the transverse momentum distributions (TMDs) for the electron in simulated QED model. We have used the overlap representation of light-front wave functions (LFWFs) where the spin-1/2 relativistic composite system consists of spin-1/2 fermion and spin-1 vector boson. The results have been obtained for T-even TMDs in transverse momentum plane for fixed value of longitudinal momentum fraction $x$.

hep-ph↗

arXiv2015

Delving into the Security Issues of Mobile Cloud Computing

Looking at the last decade, progress in technology has made a huge impact on our lifestyles. Enhanced use of mobile phones has provided a technological breakthrough, with the latest smartphones capturing the market. The word smartphone is enough for everyone to understand the tremendous potential it brought to the market in terms of economics as well as usability. Not only this, this ever growing mobile mania has a lot more to offer. The familiarity of applications like dropbox etc is a clear indication of the popularity of mobile and cloud computing. But where we get all the benefits from this computing platform, there are some of the challenges too. However, with the enhanced facilities and luxuries, some challenges are always accompanied.

cs.CR↗

arXiv2013

Soft computing techniques for software effort estimation

The effort invested in a software project is probably one of the most important and most analyzed variables in recent years in the process of project management. The limitation of algorithmic effort prediction models is their inability to cope with uncertainties and imprecision surrounding software projects at the early development stage. More recently attention has turned to a variety of machine learning methods, and soft computing in particular to predict software development effort. Soft computing is a consortium of methodologies centering in fuzzy logic, artificial neural networks, and evolutionary computation. It is important, to mention here, that these methodologies are complementary and synergistic, rather than competitive. They provide in one form or another flexible information processing capability for handling real life ambiguous situations. These methodologies are currently used for reliable and accurate estimate of software development effort, which has always been a challenge for both the software industry and academia. The aim of this study is to analyze soft computing techniques in the existing models and to provide in depth review of software and project estimation techniques existing in industry and literature based on the different test datasets along with their strength and weaknesses

cs.SE↗

arXiv2009

Biogeography based Satellite Image Classification

Biogeography is the study of the geographical distribution of biological organisms. The mindset of the engineer is that we can learn from nature. Biogeography Based Optimization is a burgeoning nature inspired technique to find the optimal solution of the problem. Satellite image classification is an important task because it is the only way we can know about the land cover map of inaccessible areas. Though satellite images have been classified in past by using various techniques, the researchers are always finding alternative strategies for satellite image classification so that they may be prepared to select the most appropriate technique for the feature extraction task in hand. This paper is focused on classification of the satellite image of a particular land cover using the theory of Biogeography based Optimization. The original BBO algorithm does not have the inbuilt property of clustering which is required during image classification. Hence modifications have been proposed to the original algorithm and the modified algorithm is used to classify the satellite image of a given region. The results indicate that highly accurate land cover features can be extracted effectively when the proposed algorithm is used.

cs.CV↗