Post-Doctoral Research Visit F/M Cooperative Inference Strategies

TN France; Provence-Alpes-Côte d'Azur; Sur place; EUR 45 000 - 75 000; Plein temps

Résumé du poste

An innovative research opportunity awaits in the realm of machine learning and inference delivery networks. This role focuses on developing strategies that optimize the balance between latency and accuracy for AI models deployed across diverse computing nodes. You'll engage in cutting-edge research while potentially supervising students and contributing to their academic growth. The position offers a dynamic environment where your mathematical expertise can directly impact real-world applications. Join a forward-thinking team that values collaboration and creativity, and enjoy flexible working arrangements along with generous leave policies.

Prestations

Partial reimbursement of public transport costs

7 weeks of annual leave

10 extra days off due to RTT

Possibility of teleworking

Flexible working hours

Professional equipment available

Social, cultural and sports events

Qualifications

• Ph.D. required in Applied Mathematics or Computer Science.
• Strong mathematical background in optimization and statistical learning.

Responsabilités

• Study inference delivery strategies for AI models in networks.
• Involve in students' supervision and teaching activities.

Connaissances

Machine Learning

Optimization

Statistical Learning

Programming Skills

PyTorch

TensorFlow

Formation

Ph.D. in Applied Mathematics

Ph.D. in Computer Science

Description du poste

Social network you want to login/join with:

col-narrow-left

Client:

INRIA

Location:

Job Category:

Other

-

EU work permit required:

Yes

col-narrow-right

Job Reference:

22eb5e89e75c

Job Views:

1

Posted:

24.04.2025

Expiry Date:

08.06.2025

col-wide

Job Description:

This PostDos is funded by the challenge Inria-Nokia Bell Labs: LearnNet (LearningNetworks).

Introduction
An increasing number of applications rely on complex inference tasks based on machine learning (ML). Currently, two options exist to run such tasks: either served directly by the end device (e.g., smartphones, IoT equipment, smart vehicles) or offloaded to a remote cloud. Both options may be unsatisfactory for many applications: local models may have inadequate accuracy, while the cloud may fail to meet delay constraints. In [SSCN], researchers from the Inria NEO and Nokia AIRL teams presented the novel idea of inference delivery networks (IDNs), networks of computing nodes that coordinate to satisfy ML inference requests achieving the best trade-off between latency and accuracy. IDNs bridge the dichotomy between device and cloud execution by integrating inference delivery at various tiers of the infrastructure continuum (access, edge, regional data center, cloud). Nodes with heterogeneous capabilities can store a set of monolithic machine-learning models with different computational/memory requirements and different accuracy and inference requests that can be forwarded to other nodes if the local answer is not considered accurate enough.

Research goal
Given an AI model’s placement in an IDN, we will study inference delivery strategies to be implemented at each node in this task. For example, a simple inference delivery strategy is to provide the inference from the local AI model if this seems to be accurate enough or to forward the input to a more accurate model at a different node if the inference quality improvement (e.g., in terms of accuracy) compensates for the additional delay or resource consumption. Besides this serve-locally-or-forward policy, we will investigate more complex inference delivery strategies, which may allow inferences from models at different clients to be combined. To this purpose, we will rely on ensemble learning approaches [MS22] like bagging [Bre96] or boosting [Sch99], adapting them to IDN characteristics. For example, in an IDN, models may or may not be trained jointly, may be trained on different datasets, and have different architectures, ruling out some ensemble learning techniques. Moreover, queries to remote models incur a cost, which leads to prefer ensemble learning techniques that do not require joint evaluation of all available models.
In an IDN, models could be jointly trained on local datasets using federated learning algorithms [KMA]. We will study how the selected inference delivery strategy may require changes to such algorithms to consider the statistical heterogeneity induced by the delivery strategy itself. For example, nodes with more sophisticated models will receive inference requests for difficult samples from nodes with simpler and less accurate models, leading to a change in the data distribution seen at inference with respect to that of the local dataset. Some preliminary results about the training for early-exit networks in this context are in [KSR].

1
References
[Bre96] Leo Breiman. Bagging predictors. Machine Learning, 24:123–140, August 1996.
[KMA] Peter Kairouz et al, Advances and Open Problems in Federated Learning. Foundations and Trends in Machine Learning, 14(1–2):1–210, 2021.
[KSR] Caelin Kaplan, Tareq Si Salem, Angelo Rodio, Chuan Xu, and Giovanni Neglia. Federated learning for cooperative inference systems: The case of early exit networks, 2024.
[MS22] Ibomoiye Domor Mienye and Yanxia Sun. A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects. IEEE Access, 10:99129–99149, 2022.
[Sch99] Robert E. Schapire. A brief introduction to boosting. In Proceedings of the 16th international joint conference on Artificial intelligence - Volume 2, IJCAI’99, pages 1401–1406, San Francisco, CA, USA, July 1999. Morgan Kaufmann Publishers Inc.
[SSCN] T. Si Salem, G. Castellano, G. Neglia, F. Pianese and A. Araldo, "Toward Inference Delivery Networks: Distributing Machine Learning With Optimality Guarantees," in IEEE/ACM Transactions on Networking, vol. 32, no. 1, pp. 859-873, Feb. 2024

Research.

If the selected candidate is interested, he/she may be involved in students' supervision (master and PhD level) and teaching activities.

Candidates must hold a Ph.D. in Applied Mathematics, Computer Science or a closely related discipline. Candidates must also show evidence of research productivity (e.g. papers, patents, presentations, etc.) at the highest level.

We prefer candidates who have a strong mathematical background (on optimization, statistical learning or privacy) and are keen on using mathematics to model real problems and gain insights. The candidate should also be knowledgeable in machine learning and have good programming skills. Previous experiences with PyTorch or TensorFlow are a plus.

Advantages

• Partial reimbursement of public transport costs
• Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
• Possibility of teleworking (after 6 months of employment) and flexible organization of working hours
• Professional equipment available (videoconferencing, loan of computer equipment, etc.)
• Social, cultural and sports events and activities