Thomas Adler

Thomas Adler


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 September 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
TAThomas Adler
Thomas Adler
JCJunda Chen
Junda Chen
WGWenqi Gu
Wenqi Gu
ZLZiheng Liao
Ziheng Liao
Carlo Vittorio CannistraciCarlo Vittorio Cannistraci
Carlo Vittorio Cannistraci
Hyperbolic geometry explains many structural features of real-world networks, yet existing hyperbolic generative network models with community organization such as the nonuniform popularity-similarity optimization (nPSO) are restricted to unipartite graphs. Here we introduce a bipartite extension of the nPSO model called nBPSO, motivated by the prevalence of community organization in real-world bipartite networks and the emerging evidence of hyperbolic hierarchical connectivity in trained sparse neural networks. nBPSO provides explicit control over link density, degree distribution, average clustering, and community organization. We engineer the model to generate consecutive and concatenated bipartite layers, enabling initialization of dynamic sparse training multilayer perceptron neural networks with tunable hyperbolic organization for each layer. We find that task-agnostic (unaligned with the task) hyperbolic random network initialization degrades the performance of sparse neural networks compared with uniform random initialization. This degradation arises because the hyperbolic random initialization imposes an arbitrary hierarchical prior into the sparse topology. Dynamic sparse training may then need to optimize the weights and reorganize this arbitrary task-agnostic hierarchy into a task-driven one. By contrast, a uniform random initialization imposes at start less structural bias and may therefore be easier to reconfigure during training toward the hierarchical topology suited to the task. This work motivates the need for data-informed hyperbolic initialization methods which generate sparse topologies with a hierarchical prior closer to the task, facilitating the further learning of a task-oriented hierarchical organization during dynamic sparse training. In addition, nBPSO represents the first hyperbolic bipartite network generative model that allows the mesoscale community structure to be explicitly controlled through model parameters, making it a useful tool for broader complex systems applications where community organization is central to accurate and interpretable modeling.

8 December 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
TAThomas Adler
Thomas Adler
Marco GrassiaMarco Grassia
Marco Grassia
ZLZiheng Liao
Ziheng Liao
Giuseppe MangioniGiuseppe Mangioni
Giuseppe Mangioni
Carlo Vittorio CannistraciCarlo Vittorio Cannistraci
Carlo Vittorio Cannistraci
Complex networks model the structure and function of critical technological, biological, and communication systems. Network dismantling, the targeted removal of nodes to fragment a network, is essential for analyzing and improving system robustness. Existing dismantling methods suffer from key limitations: they depend on global structural knowledge, exhibit slow running times on large networks, and overlook the network’s latent geometry, a key feature known to govern the dynamics of complex systems. Motivated by these findings, we introduce Latent Geometry-Driven Network Automata (LGD-NA), a novel framework that leverages local network automata rules to approximate effective link distances between interacting nodes. LGD-NA is able to identify critical nodes and capture latent manifold information of a network for effective and efficient dismantling. We show that this latent geometry-driven approach outperforms all existing dismantling algorithms, including spectral Laplacian-based methods and machine learning ones such as graph neural networks and . We also find that a simple common-neighbor-based network automata rule achieves near state-of-the-art performance, highlighting the effectiveness of minimal local information for dismantling. LGD-NA is extensively validated on the largest and most diverse collection of real-world networks to date (1,475 real-world networks across 32 complex systems domains) and scales efficiently to large networks via GPU acceleration. Finally, we leverage the explainability of our common-neighbor approach to engineer network robustness, substantially increasing the resilience of real-world networks. We validate LGD-NA's practical utility on domain-specific functional metrics, spanning neuronal firing rates in the Drosophila Connectome, transport efficiency in flight maps, outbreak sizes in contact networks, and communication pathways in terrorist cells. Our results confirm latent geometry as a fundamental principle for understanding the robustness of real-world systems, adding dismantling to the growing set of processes that network geometry can explain.

16 October 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
EBEunhye Baek
Eunhye Baek
QZQingtian Zhang
Qingtian Zhang
TAThomas Adler
Thomas Adler
KBKangyou Bao
Kangyou Bao
ZRZhao Rong
Zhao Rong
Carlo Vittorio CannistraciCarlo Vittorio Cannistraci
Carlo Vittorio Cannistraci
Neuromorphic AI increasingly draws on sparse dendritic computation, yet a network-science framework linking sub-neuronal circuit organization to function remains underdeveloped. Here we introduce the neural processing component (NPC) paradigm, representing synapses, dendrites, somata and axons as network elements whose sparse topology shapes computation. We implement this paradigm in a dendritic reservoir-based network for trajectory detection, demonstrating in device-informed simulations that real-time motion trajectories can be detected through fixed NPC design rather than training. Using hyperbolic network geometry, we reveal that NPC neuromorphic circuits with dendrites possess latent hierarchical and modular organization that is not visible from circuit diagrams alone. We further show that this geometric representation identifies vulnerable modules and critical routing nodes that can be selectively redesigned, reducing detection error under router-node failure by 50.9%. These results establish NPC network geometry as a method for circuit-level interpretability androbustness-oriented design of sparse neuromorphic AI.

29 September 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
TAThomas Adler
Thomas Adler
DCDiego Cerretti
Diego Cerretti
Carlo Vittorio CannistraciCarlo Vittorio Cannistraci
Carlo Vittorio Cannistraci
Sparse neural networks can substantially reduce computational and memory costs, yet their performance remains highly sensitive to the choice of sparse topology, particularly at extreme sparsity, where they struggle to outperform fully connected models. Existing sparse initialization methods are predominantly structure-driven and rarely conditioned on the data, motivating a central question: how can sparse connectivity be organized in a principled way that reflects the structure of the data rather than relying on predefined or heuristic topologies? Network science has shown that complex network topology can be characterized by an underlying latent geometry, helping to explain processes such as network routing, navigation, and dismantling. This suggests that, rather than imposing a predefined sparse topology, one can extract the latent geometry of the data and use it to organize network connectivity. Motivated by this connection, we introduce Geometric Supercharger (GS), a data-informed framework for hyperbolic initialization of MLP-based sparse neural networks. GS extracts pairwise feature relationships using Pearson correlation and constructs a macro-scale geometric embedding through shortest-path-based pre-weighting and dimensionality reduction. The resulting geometry is then reused to reweight the network and refine the embedding, thereby supercharging it. This supercharged embedding is followed by meso-scale refinement based on community detection and angular reordering. The final angular coordinates encode data-informed node similarity and are used to generate a sparse hyperbolic topology. Building on previous findings that arbitrary, data-agnostic hyperbolic hierarchies can hinder sparse neural network training, we show that making the hierarchy data-informed turns the same geometric prior into a performance advantage. We evaluate Geometric Supercharger across four diverse tasks: image classification, physics-informed neural networks, reinforcement learning, and stock-market prediction. GS achieves state-of-the-art performance among all evaluated static sparse initialization methods in the ultra-sparse 99% regime and outperforms fully connected networks in the majority of experiments at 90% and 99% sparsity. These findings establish data-informed latent geometry as an important organizing principle for sparse MLP initialization and motivate a broader class of geometry-driven sparse neural networks.