Dissertations - M Tech (CS)

Permanent URI for this collectionhttps://dspace.isical.ac.in/handle/10263/2147

These Dissertations were submitted in partial fulfilment of the requirements for the award of M TECH (Computer Science) Degree of Indian Statistical Institute

Browse

Start date: 2025Subject: search.filters.subject.Graph Neural Networks

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Deep Reinforcement Learning with Directed Asymmetry and Kolmogorov-Arnold Networks for Dismantling Interdependent Multiplex Networks
    (Indian Statistical Institute, 2026-06-16) Dev, Soumyajit
    Identifying the minimum-cost node-removal sequence that fragments a complex network - the network dismantling problem is NP-hard and central to infrastructure resilience. In interdependent multiplex networks, this difficulty is compounded by cascading cross-layer failures. While deep reinforcement learning (DRL) agents utilizing graph neural network (GNN) encoders achieve near-optimal dismantling, current state-of-the-art architectures suffer from two critical limitations. Topologically, existing agents strictly assume undirected edges, rendering them inapplicable to directed systems - such as supply chains or gene regulatory cascades - where failure propagation is fundamentally asymmetric. To resolve this, we propose Disassembling Directed Interdependent Networks (DDIN). DDIN introduces an asymmetric GraphSAGE encoder that explicitly separates incoming influence from outgoing control aggregations, paired with a multi-relational attention mechanism for cross-layer dependency fusion. Evaluated zero-shot on five real-world directed networks, DDIN achieves a 16-23% reduction in the Area Under the Dismantling Curve (AUDC) over heuristic baselines. Functionally, existing GNN encoders parameterise message-passing through multi-layer perceptrons (MLPs). These fixed-affine projections lack the capacity to model the non-smooth, high-frequency vulnerability patterns governing cascading fragility in scale-free topologies. We address this by proposing Kolmogorov-Arnold Reinforcement Learning (KARL), the first architecture to embed learnable univariate functions into an off-policy DRL combinatorial optimiser. KARL features a residual B-spline KAN encoder to stabilise gradient norms during deep message-passing, a fully KAN-parameterised cross-layer attention module (KANformer), and an orthogonal Chebyshev-KAN action-value head to mitigate boundary oscillations under non-stationary temporal-difference targets. Evaluated zero-shot on six real-world undirected multiplex networks, KARL yields a 21.96% average AUDC improvement over state-of-the-art baselines, alongside emergent structural interpretability. By independently resolving the directed topology limitation and the affine expressivity bottleneck, this dissertation establishes a robust architectural foundation for structurally faithful network dismantling models.
  • Thumbnail Image
    Item
    Multi-Frequency Associative Memory for Continual Graph Learning through Nested Optimization
    (2026-06-16) Kundu, Shuvam
    Graph Neural Networks struggle to learn new tasks without forgetting old ones a problem known as catastrophic forgetting. In graph domains, this is compounded by structural shift, where newly added edges corrupt the learned representations of historical nodes even when model weights remain unchanged. We present CAM-Titans, a continual graph learning framework built around a two-buffer associative memory to address both parametric and structural forgetting. Our architecture operates across three timescales of adaptation: a slow base memory updated via ordinary gradient descent, an intermediate task buffer re-encoded after every task using the delta-rule, and a transient in-context state for rapid within-pass adaptation. To ensure historical class prototypes remain retrievable as the network backbone evolves, memory retrieval is anchored in a dynamically maintained prototype coordinate system. Furthermore, a cosine classifier mitigates magnitude imbalance, preventing older classes from dominating predictions. Empirical evaluations across diverse continual learning benchmarks demonstrate that CAM-Titans effectively mitigates catastrophic forgetting, achieving superior stability and accuracy in both Task-Incremental and Class-Incremental settings.
  • No Thumbnail Available
    Item
    Detection of Fake News in Short Videos: A Multimodal Approach
    (Indian Statistical Institute, Kolkata, 2025-06) Kumari, Mona
    The rise of generative models and affordable video editing tools has fueled the spread of fake and manipulated videos, undermining information reliabilityespecially on social media. Traditional detection methods, focused on single modalities like visual artifacts or text cues, often struggle with diverse, user-generated content. This dissertation presents a unified framework for fake video detection that integrates multimodal semantics, narrative structure, and propagation behavior. Visual, audio, text, and OCR features are extracted using pretrained models (CLIP, Wav2Vec2), and segment-level graphs are built to model narrative flow using Graph Attention Networks (GATv2Conv). User engagement dynamics are modeled via a bidirectional LSTM. A cross-modal consistency loss encourages semantic alignment across modalities, improving representational coherence. The end-to-end model is evaluated on heterogeneous datasets like FakeTT, demonstrating strong generalization and robustness. Results show the proposed system outperforms existing baselines, especially in challenging cases with asynchronous or fragmented content. By combining content, structure, and behavioral cues, the framework enables more reliable and interpretable fake video detection.