arXiv subjects

Deepayan Chakrabarti

Publications and source records attributed to Deepayan Chakrabarti.

17 recordsLinked to original sources

arXiv2026

When Does Context Routing Help? A Systematic Study of Multi-Modal Fusion in Time Series Forecasting

Multi-modal time series forecasting methods integrate auxiliary context into temporal predictions through increasingly sophisticated fusion mechanisms. A growing body of work reports substantial gains, yet it is often unclear whether they reflect genuine use of the context or incidental architectural effects. We ask a narrower, checkable question: when can auxiliary context help a forecaster at all? We identify two dataset-level conditions that must both hold: (1) the target is not dominated by a last-value shortcut (low autocorrelation rho_h), and (2) the context carries information about the target beyond history (non-zero conditional mutual information delta; when delta=0 no predictor can benefit---a distribution-free result). Through controlled experiments on MoME (a 14.3B-parameter mixture-of-experts model, 6 datasets, 10 seeds) and four additional fusion mechanisms implemented within a single-backbone testbed (5 datasets), we find that when both conditions hold, text-conditioned expert modulation contributes a sizeable MSE reduction; when either fails, the contribution collapses to the capacity floor of the modulation pathway and carries no context-attributable signal. We establish causality through two interventions: adding a shortcut to MoME suppresses routing contribution by 77-93% across 3 datasets; progressively corrupting context quality drives the context-specific benefit from +44% to negative. We validate the autocorrelation component of our diagnostic on 27 Monash Archive datasets. We provide a calibrated pre-training diagnostic that, on the datasets we test, yields no false positives in well-powered settings. We are explicit about the asymmetry of our evidence: the negative arm is broadly reliable, while the large positive magnitudes come from a single model family (MoME) and are corroborated only in direction by the testbed.

cs.LG↗

arXiv2026

From Accuracy to Auditability: A Survey of Determinism in Financial AI Systems

Deploying machine learning in regulated financial environments -- credit risk, fraud detection, and anti-money laundering -- exposes critical vulnerabilities in algorithmic reproducibility. While early financial ML addressed statistical challenges such as backtest overfitting, deep neural networks and Generative AI have introduced mechanical nondeterminism rooted in hardware and architecture. This survey provides a systems perspective on reproducibility failures across three modalities now dominant in financial AI: tabular models (post-hoc explanation variance), graph networks (stochastic sampling and temporal asynchrony), and LLM-based agentic workflows (batch-dependent divergence and trajectory drift). We supplement the literature analysis with first-party experiments on public financial datasets -- quantifying explanation rank instability in credit scoring, prediction flip rates in GNN-based fraud detection, and tensor-parallel-induced output divergence in LLM entity extraction. We propose a layered evaluation framework linking modality-specific metrics (RBO, D_cos, TDI, PSD) to audit readiness, and report where these measures overlap rather than complement one another.

cs.AI↗

arXiv2026

COPYCOP: Ownership Verification for Graph Neural Networks

Given two GNNs that output node embeddings, how can we determine if they were trained independently? An adversary could have trained one GNN specifically to mimic the other GNN's embeddings. To obscure this relationship between the GNNs, the adversarial GNN might then transform its output embeddings. The two GNNs could have different architectures, weights, and embedding dimensions, and the adversary can transform the embeddings. Despite these stringent conditions, our algorithm (named CopyCop) can identify such copycat GNNs, unlike existing watermarking and fingerprinting methods. We also provide theoretical guarantees for CopyCop. Finally, experiments on 14 datasets and 5 GNN architectures demonstrate that CopyCop is accurate and robust against a broad class of adversarial attacks and transformations. Code is available at: https://anonymous.4open.science/r/CopyCop-Graph-Ownership-Verification-8143/README.md

cs.LG↗

arXiv2026

SPADE: Faster Drug Discovery by Learning from Sparse Data

Drug discovery seeks molecules (ligands) that bind strongly and selectively to a target protein. However, fewer than 5% of candidate ligands pass the bar for even the early stages of drug discovery. Furthermore, we want methods that work for novel proteins for which we have no prior data. Starting from scratch, we have to iteratively select and test candidate ligands such that we find enough ligands of the desired quality in as few tests as possible. Our proposed algorithm, named SPADE, introduces a novel approach to ligand selection that requires only 40 tests on average to find 10 high-quality ligands. In one-vs-one comparisons, SPADE outperforms deep learning and Bayesian optimization methods on more proteins, achieving median improvements of 7%-32% in sample efficiency. SPADE is also 10x faster than its closest competitor at scoring candidate drugs. Dataset and code is available at https://anonymous.4open.science/r/SPADE_Fast_Drug_Discovery_by_Learning_from_Sparse_Data-F028/README.md

cs.LG↗

arXiv2026

Learning to Query History: Nonstationary Classification via Learned Retrieval

Nonstationarity is ubiquitous in practical classification settings, leading deployed models to perform poorly even when they generalize well to holdout sets available at training time. We address this by reframing nonstationary classification as time series prediction: rather than predicting from the current input alone, we condition the classifier on a sequence of historical labeled examples that extends beyond the training cutoff. To scale to large sequences, we introduce a learned discrete retrieval mechanism that samples relevant historical examples via input-dependent queries, trained end-to-end with the classifier using a score-based gradient estimator. This enables the full corpus of historical data to remain on an arbitrary filesystem during training and deployment. Experiments on synthetic benchmarks and Amazon Reviews '23 (electronics category) show improved robustness to distribution shift compared to standard classifiers, with VRAM scaling predictably as the length of the historical data sequence increases.

cs.LG↗

arXiv2025

GraphWeave: Interpretable and Robust Graph Generation via Random Walk Trajectories

Given a set of graphs from some unknown family, we want to generate new graphs from that family. Recent methods use diffusion on either graph embeddings or the discrete space of nodes and edges. However, simple changes to embeddings (say, adding noise) can mean uninterpretable changes in the graph. In discrete-space diffusion, each step may add or remove many nodes/edges. It is hard to predict what graph patterns we will observe after many diffusion steps. Our proposed method, called GraphWeave, takes a different approach. We separate pattern generation and graph construction. To find patterns in the training graphs, we see how they transform vectors during random walks. We then generate new graphs in two steps. First, we generate realistic random walk "trajectories" which match the learned patterns. Then, we find the optimal graph that fits these trajectories. The optimization infers all edges jointly, which improves robustness to errors. On four simulated and five real-world benchmark datasets, GraphWeave outperforms existing methods. The most significant differences are on large-scale graph structures such as PageRank, cuts, communities, degree distributions, and flows. GraphWeave is also 10x faster than its closest competitor. Finally, GraphWeave is simple, needing only a transformer and standard optimizers.

cs.LG↗

arXiv2024

Strategic Negotiations in Endogenous Network Formation

In network formation games, agents form edges with each other to maximize their utility. Each agent's utility depends on its private beliefs and its edges in the network. Strategic agents can misrepresent their beliefs to get a better resulting network. Most prior works in this area consider honest agents or a single strategic agent. Instead, we propose a model where any subset of agents can be strategic. We provide an efficient algorithm for finding the set of Nash equilibria, if any exist, and certify their nonexistence otherwise. We also show that when several strategic agents are present, their utilities can increase or decrease compared to when they are all honest. Small changes in the inter-agent correlations can cause such shifts. In contrast, the simpler one-strategic-agent setting explored in the literature lacks such complex patterns. Finally, we develop an algorithm by which new agents can learn the information needed for strategic behavior. Our algorithm works even when the (unknown) strategic agents deviate from the Nash-optimal strategies. We verify these results on both simulated networks and a real-world dataset on international trade.

math.OC↗

arXiv2022

Incentive-Aware Models of Financial Networks

Financial networks help firms manage risk but also enable financial shocks to spread. Despite their importance, existing models of financial networks have several limitations. Prior works often consider a static network with a simple structure (e.g., a ring) or a model that assumes conditional independence between edges. We propose a new model where the network emerges from interactions between heterogeneous utility-maximizing firms. Edges correspond to contract agreements between pairs of firms, with the contract size being the edge weight. We show that, almost always, there is a unique "stable network." All edge weights in this stable network depend on all firms' beliefs. Furthermore, firms can find the stable network via iterative pairwise negotiations. When beliefs change, the stable network changes. We show that under realistic settings, a regulator cannot pin down the changed beliefs that caused the network changes. Also, each firm can use its view of the network to inform its beliefs. For instance, it can detect outlier firms whose beliefs deviate from their peers. But it cannot identify the deviant belief: increased risk-seeking is indistinguishable from increased expected profits. Seemingly minor news may settle the dilemma, triggering significant changes in the network.

math.OC↗

arXiv2021

Robust Linear Classification from Limited Training Data

We consider the problem of linear classification under general loss functions in the limited-data setting. Overfitting is a common problem here. The standard approaches to prevent overfitting are dimensionality reduction and regularization. But dimensionality reduction loses information, while regularization requires the user to choose a norm, or a prior, or a distance metric. We propose an algorithm called RoLin that needs no user choice and applies to a large class of loss functions. RoLin combines reliable information from the top principal components with a robust optimization to extract any useful information from unreliable subspaces. It also includes a new robust cross-validation that is better than existing cross-validation methods in the limited-data setting. Experiments on $25$ real-world datasets and three standard loss functions show that RoLin broadly outperforms both dimensionality reduction and regularization. Dimensionality reduction has $14\%-40\%$ worse test loss on average as compared to RoLin. Against $L_1$ and $L_2$ regularization, RoLin can be up to 3x better for logistic loss and 12x better for squared hinge loss. The differences are greatest for small sample sizes, where RoLin achieves the best loss on 2x to 3x more datasets than any competing method. For some datasets, RoLin with $15$ training samples is better than the best norm-based regularization with $1500$ samples.

cs.LG↗

arXiv2019

Estimating Mixed Memberships with Sharp Eigenvector Deviations

We consider the problem of estimating community memberships of nodes in a network, where every node is associated with a vector determining its degree of membership in each community. Existing provably consistent algorithms often require strong assumptions about the population, are computationally expensive, and only provide an overall error bound for the whole community membership matrix. This paper provides uniform rates of convergence for the inferred community membership vector of each node in a network generated from the Mixed Membership Stochastic Blockmodel (MMSB); to our knowledge, this is the first work to establish per-node rates for overlapping community detection in networks. We achieve this by establishing sharp row-wise eigenvector deviation bounds for MMSB. Based on the simplex structure inherent in the eigen-decomposition of the population matrix, we build on established corner-finding algorithms from the optimization community to infer the community membership vectors. Our results hold over a broad parameter regime where the average degree only grows poly-logarithmically with the number of nodes. Using experiments with simulated and real datasets, we show that our method achieves better error with lower variability over competing methods, and processes real world networks of up to 100,000 nodes within tens of seconds.

stat.ML↗

arXiv2018

Overlapping Clustering Models, and One (class) SVM to Bind Them All

People belong to multiple communities, words belong to multiple topics, and books cover multiple genres; overlapping clusters are commonplace. Many existing overlapping clustering methods model each person (or word, or book) as a non-negative weighted combination of "exemplars" who belong solely to one community, with some small noise. Geometrically, each person is a point on a cone whose corners are these exemplars. This basic form encompasses the widely used Mixed Membership Stochastic Blockmodel of networks (Airoldi et al., 2008) and its degree-corrected variants (Jin et al., 2017), as well as topic models such as LDA (Blei et al., 2003). We show that a simple one-class SVM yields provably consistent parameter inference for all such models, and scales to large datasets. Experimental results on several simulated and real datasets show our algorithm (called SVM-cone) is both accurate and scalable.

stat.ML↗

arXiv2017

On Mixed Memberships and Symmetric Nonnegative Matrix Factorizations

The problem of finding overlapping communities in networks has gained much attention recently. Optimization-based approaches use non-negative matrix factorization (NMF) or variants, but the global optimum cannot be provably attained in general. Model-based approaches, such as the popular mixed-membership stochastic blockmodel or MMSB (Airoldi et al., 2008), use parameters for each node to specify the overlapping communities, but standard inference techniques cannot guarantee consistency. We link the two approaches, by (a) establishing sufficient conditions for the symmetric NMF optimization to have a unique solution under MMSB, and (b) proposing a computationally efficient algorithm called GeoNMF that is provably optimal and hence consistent for a broad parameter regime. We demonstrate its accuracy on both simulated and real-world datasets.

stat.ML↗

arXiv2014

Joint Inference of Multiple Label Types in Large Networks

We tackle the problem of inferring node labels in a partially labeled graph where each node in the graph has multiple label types and each label type has a large number of possible labels. Our primary example, and the focus of this paper, is the joint inference of label types such as hometown, current city, and employers, for users connected by a social network. Standard label propagation fails to consider the properties of the label types and the interactions between them. Our proposed method, called EdgeExplain, explicitly models these, while still enabling scalable inference under a distributed message-passing architecture. On a billion-node subset of the Facebook social network, EdgeExplain significantly outperforms label propagation for several label types, with lifts of up to 120% for recall@1 and 60% for recall@3.

cs.LG↗

arXiv2013

Nonparametric Link Prediction in Large Scale Dynamic Networks

We propose a nonparametric approach to link prediction in large-scale dynamic networks. Our model uses graph-based features of pairs of nodes as well as those of their local neighborhoods to predict whether those nodes will be linked at each time step. The model allows for different types of evolution in different parts of the graph (e.g, growing or shrinking communities). We focus on large-scale graphs and present an implementation of our model that makes use of locality-sensitive hashing to allow it to be scaled to large problems. Experiments with simulated data as well as five real-world dynamic graphs show that we outperform the state of the art, especially when sharp fluctuations or nonlinearities are present. We also establish theoretical properties of our estimator, in particular consistency and weak convergence, the latter making use of an elaboration of Stein's method for dependency graphs.

stat.ML↗

arXiv2012

Nonparametric Link Prediction in Dynamic Networks

We propose a non-parametric link prediction algorithm for a sequence of graph snapshots over time. The model predicts links based on the features of its endpoints, as well as those of the local neighborhood around the endpoints. This allows for different types of neighborhoods in a graph, each with its own dynamics (e.g, growing or shrinking communities). We prove the consistency of our estimator, and give a fast implementation based on locality-sensitive hashing. Experiments with simulated as well as five real-world dynamic graphs show that we outperform the state of the art, especially when sharp fluctuations or non-linearities are present.

cs.LG↗

arXiv2010

Got the Flu (or Mumps)? Check the Eigenvalue!

For a given, arbitrary graph, what is the epidemic threshold? That is, under what conditions will a virus result in an epidemic? We provide the super-model theorem, which generalizes older results in two important, orthogonal dimensions. The theorem shows that (a) for a wide range of virus propagation models (VPM) that include all virus propagation models in standard literature (say, [8][5]), and (b) for any contact graph, the answer always depends on the first eigenvalue of the connectivity matrix. We give the proof of the theorem, arithmetic examples for popular VPMs, like flu (SIS), mumps (SIR), SIRS and more. We also show the implications of our discovery: easy (although sometimes counter-intuitive) answers to `what-if' questions; easier design and evaluation of immunization policies, and significantly faster agent-based simulations.

physics.soc-ph↗

arXiv2009

Kronecker Graphs: An Approach to Modeling Networks

How can we model networks with a mathematically tractable model that allows for rigorous analysis of network properties? Networks exhibit a long list of surprising properties: heavy tails for the degree distribution; small diameters; and densification and shrinking diameters over time. Most present network models either fail to match several of the above properties, are complicated to analyze mathematically, or both. In this paper we propose a generative model for networks that is both mathematically tractable and can generate networks that have the above mentioned properties. Our main idea is to use the Kronecker product to generate graphs that we refer to as "Kronecker graphs". First, we prove that Kronecker graphs naturally obey common network properties. We also provide empirical evidence showing that Kronecker graphs can effectively model the structure of real networks. We then present KronFit, a fast and scalable algorithm for fitting the Kronecker graph generation model to large real networks. A naive approach to fitting would take super- exponential time. In contrast, KronFit takes linear time, by exploiting the structure of Kronecker matrix multiplication and by using statistical simulation techniques. Experiments on large real and synthetic networks show that KronFit finds accurate parameters that indeed very well mimic the properties of target networks. Once fitted, the model parameters can be used to gain insights about the network structure, and the resulting synthetic graphs can be used for null- models, anonymization, extrapolations, and graph summarization.

stat.ML↗