Searcharxiv⌕ Search

arXiv subjects

Parham Eftekhar

Publications and source records attributed to Parham Eftekhar.

5 recordsLinked to original sources

Deep Unrolling of Lanczos-based Laplacian Eigensolver for Crop Classification in Satellite Images

Per-pixel crop classification in satellite images is an important pre-processing step in remote crop monitoring. Leveraging progress in signed graph signal processing, we build an interpretable and lightweight neural network for binary crop classification (e.g., corn versus non-corn) in two stages: i) learn a signed graph from data, and ii) unroll a Lanczos-based eigensolver to compute the eigenvector $\u_1$ associated with the smallest eigenvalue of a hybrid graph Laplacian $\cL$ for spectral clustering. Specifically, we first construct a near-balanced signed graph $\cG^s$, where signed edge weights $w_{i,j}\in(-1,1)$ are computed from learned feature distances $d_{i,j}$ via a hyperbolic tangent mapping. Given $\cG^s$, we estimate $\u_1$ by unrolling the Lanczos algorithm and use $\mathrm{sign}(\u_1)$ for binary classification. Mathematically, we develop a theorem establishing conditions under which $\u_1$ can be well approximated after finite Lanczos iterations. Motivated by this theorem, we relax the classical Lanczos orthogonality constraints during unrolling and optimize end-to-end classification performance while promoting the derived conditions for accurate eigenvector approximation. Experiments on real-world Harmonized Landsat-Sentinel imagery show classification performance comparable to state-of-the-art deep learning models while reducing parameters by up to two orders of magnitude.

eess.SP↗

Unrolling Lanczos for Ideal Low-pass Graph Filter Approximation

Low-pass (LP) filtering is a fundamental operation in graph signal processing (GSP). Among finite-order nodal-domain methods, Lanczos-based filtering provides more accurate approximations of ideal LP filters than Chebyshev polynomial methods. We show that the approximation of Lanczos filtering can be further improved through algorithm unrolling and data-driven parameter learning. The key insight is that, because ideal LP filtering is a projection operation into the low-frequency eigen-subspace $\cS_K$, instead of approximating individual eigen-pairs of a graph Laplacian $Ł$ as done in classical Lanczos, an unrolled Lanczos network can directly approximate $\cS_K$. Specifically, we first establish a theorem identifying properties of the Lanczos tridiagonal matrix $\T_m$ that promote accurate approximation of the low-frequency eigen-subspace $\cS_K$. Guided by this theory, we relax the orthogonality constraint on Lanczos vectors, resulting in Ritz vectors that better span $\cS_K$. To ensure numerical stability, we constrain $\T_m$ to be similar to a symmetric matrix, thereby guaranteeing real-valued eigenvalues. Experimental results on random graphs and learned graphs in two natural language processing (NLP) tasks show that our unrolled Lanczos network achieves superior ideal LP filter approximation compared to the classical Lanczos method.

eess.SP↗

HypergraphFormer: Learning Hypergraphs from LLMs for Editable Floor Plan Generation

In this work, we propose HypergraphFormer, a novel and efficient approach to floor plan generation based on learning hypergraph representations with a large language model (LLM). The model is trained via supervised fine-tuning to generate a hypergraph-based textual representation that encodes spatial relationships and connectivity information within floor plans. We train and evaluate our approach on the RPLAN dataset, and further demonstrate its generalizability on a separate out-of-distribution dataset, which we release in this paper. Our method outperforms state-of-the-art techniques based on rasterized or vectorized representations across a diverse set of metrics. We also show improved data efficiency, particularly under distribution shift. The hypergraph formulation enables the generation of floor plans for arbitrary, irregular, user-specified boundaries by decoupling apartment footprints from their functional and geometric subdivisions. Furthermore, we show that the proposed methodology offers a high degree of editability, making it particularly well suited to design-oriented workflows supported by LLMs.

cs.LG↗

Lightweight Transformer for EEG Classification via Balanced Signed Graph Algorithm Unrolling

Samples of brain signals collected by EEG sensors have inherent anti-correlations that are well modeled by negative edges in a finite graph. To differentiate epilepsy patients from healthy subjects using collected EEG signals, we build lightweight and interpretable transformer-like neural nets by unrolling a spectral denoising algorithm for signals on a balanced signed graph -- graph with no cycles of odd number of negative edges. A balanced signed graph has well-defined frequencies that map to a corresponding positive graph via similarity transform of the graph Laplacian matrices. We implement an ideal low-pass filter efficiently on the mapped positive graph via Lanczos approximation, where the optimal cutoff frequency is learned from data. Given that two balanced signed graph denoisers learn posterior probabilities of two different signal classes during training, we evaluate their reconstruction errors for binary classification of EEG signals. Experiments show that our method achieves classification performance comparable to representative deep learning schemes, while employing dramatically fewer parameters.

cs.LG↗

Interpretable Lightweight Transformer via Unrolling of Learned Graph Smoothness Priors

We build interpretable and lightweight transformer-like neural networks by unrolling iterative optimization algorithms that minimize graph smoothness priors -- the quadratic graph Laplacian regularizer (GLR) and the $\ell_1$-norm graph total variation (GTV) -- subject to an interpolation constraint. The crucial insight is that a normalized signal-dependent graph learning module amounts to a variant of the basic self-attention mechanism in conventional transformers. Unlike "black-box" transformers that require learning of large key, query and value matrices to compute scaled dot products as affinities and subsequent output embeddings, resulting in huge parameter sets, our unrolled networks employ shallow CNNs to learn low-dimensional features per node to establish pairwise Mahalanobis distances and construct sparse similarity graphs. At each layer, given a learned graph, the target interpolated signal is simply a low-pass filtered output derived from the minimization of an assumed graph smoothness prior, leading to a dramatic reduction in parameter count. Experiments for two image interpolation applications verify the restoration performance, parameter efficiency and robustness to covariate shift of our graph-based unrolled networks compared to conventional transformers.

cs.LG↗