Arko Mukherjee

Susheel Suresh, Danny Godbout, Arko Mukherjee et al. · microsoft-research

Federated graph representation learning (FedGRL) brings the benefits of distributed training to graph structured data while simultaneously addressing some privacy and compliance concerns related to data curation. However, several interesting real-world graph data characteristics viz. label deficiency and downstream task heterogeneity are not taken into consideration in current FedGRL setups. In this paper, we consider a realistic and novel problem setting, wherein cross-silo clients have access to vast amounts of unlabeled data with limited or no labeled data and additionally have diverse downstream class label domains. We then propose a novel FedGRL formulation based on model interpolation where we aim to learn a shared global model that is optimized collaboratively using a self-supervised objective and gets downstream task supervision through local client models. We provide a specific instantiation of our general formulation using BGRL a SoTA self-supervised graph representation learning method and we empirically verify its effectiveness through realistic cross-slio datasets: (1) we adapt the Twitch Gamer Network which naturally simulates a cross-geo scenario and show that our formulation can provide consistent and avg. 6.1% gains over traditional supervised federated learning objectives and on avg. 1.7% gains compared to individual client specific self-supervised training and (2) we construct and introduce a new cross-silo dataset called Amazon Co-purchase Networks that have both the characteristics of the motivated problem setting. And, we witness on avg. 11.5% gains over traditional supervised federated learning and on avg. 1.9% gains over individually trained self-supervised models. Both experimental results point to the effectiveness of our proposed formulation. Finally, both our novel problem setting and dataset contributions provide new avenues for the research in FedGRL.

Junxuan Li, Ryan Wickman, Sahil Bhatnagar et al. · microsoft-research

Operations research (OR) uses mathematical models to enhance decision-making, but developing these models requires expert knowledge and can be time-consuming. Automated mathematical programming (AMP) has emerged to simplify this process, but existing systems have limitations. This paper introduces a novel methodology that uses recent advances in Large Language Model (LLM) to create and edit OR solutions from non-expert user queries expressed using Natural Language. This reduces the need for domain expertise and the time to formulate a problem. The paper presents an end-to-end pipeline, named NL2OR, that generates solutions to OR problems from natural language input, and shares experimental results on several important OR problems.

Subhojyoti Mukherjee, Stefano Petrangeli, Branislav Kveton et al.

Direct prompt-based editing often fails on complex transformations because vague and subjective prompts often require nuanced understanding of what should be changed in the image. Our core intuition is that leveraging compositional image editing tools rather than direct prompting profits from structured agent-level planning with explicit reasoning, leading to better results. This structured planning framework enables efficient offline RL post-training on quality-scored trajectories to improve performance. We present a tool-based agentic RL post-training framework that addresses this through structured planning with chain-of-thought reasoning. Our key contributions include: (1) A tool-based agentic planning methodology that combines a compositional library of orthogonal primitive transformations, structured context representation, and explicit per-step reasoning to decompose complex styling into interpretable tool sequences. (2) A synthetic data generation pipeline producing three large-scale datasets (each $\sim$10K trajectories) with reasoning chains, plans, and quality scores, as no existing datasets provide such supervision. Our datasets and code are publicly available at the HuggingFace repository. (3) Offline RL training methods for learning planners with reasoning as our core algorithmic contributions, which consistently improve over the Edit-Only baseline in visual quality and instruction following. (4) Comprehensive evaluation across 4B and 8B parameter Qwen3-VL models showing that our methods outperform other baselines in the majority of compositional tasks, validated by human evaluations.