wayground logo

Free Printable Worksheets

NEW

Font size

S
M
L
XL
Worksheets

Federated Learning Quiz

Total questions: 20

Worksheet time: 10mins

Name
Class
Date
1.

Which feature most effectively differentiates Federated Learning from Centralized Machine Learning?

a)

Higher computational power at server

b)

Centralized data storage

c)

Local model training on client data

d)

Faster convergence rate

2.

Federated Learning primarily emerged due to:

a)

Increased GPU availability

b)

Growth of cloud-only applications

c)

Privacy regulations and edge device proliferation

d)

Decline in distributed systems

3.

Which scenario best justifies using Federated Learning over Distributed ML?

a)

High-speed data center networks

b)

Public benchmark datasets

c)

Sensitive user data across personal devices

d)

Homogeneous server clusters

4.

In comparison to Distributed ML, Federated Learning reduces privacy risks mainly because:

a)

Data is encrypted at rest

b)

Raw data never leaves client devices

c)

Models are smaller

d)

Training is asynchronous

5.

Which limitation is most prominent in Federated Learning but not in Centralized ML?

a)

Model bias

b)

Communication overhead

c)

Overfitting

d)

Feature scaling

6.

Horizontal Federated Learning is best suited when:

a)

Clients share features but not samples

b)

Clients share samples but not features

c)

Clients share neither samples nor features

d)

Clients share labels only

7.

Vertical Federated Learning is most applicable when:

a)

Data samples are identical across clients

b)

Feature spaces are identical

c)

Data belongs to the same users but different features

d)

Training happens on edge devices only

8.

Transfer Learning based Federated Learning is preferred when:

a)

Clients have identical datasets

b)

Data distributions differ significantly across clients

c)

Bandwidth is unlimited

d)

Labels are unavailable

9.

Which factor makes Vertical FL more complex than Horizontal FL?

a)

Larger datasets

b)

Requirement of secure feature alignment

c)

Absence of aggregation

d)

Higher bandwidth

10.

In the Federated Learning ecosystem, the central server’s primary role is to:

a)

Store raw training data

b)

Perform feature extraction

c)

Aggregate client model updates

d)

Label datasets

11.

Which stakeholder directly controls data privacy in Federated Learning?

a)

Central server

b)

Cloud provider

c)

Data owners / clients

d)

Application developer

12.

Malicious clients in Federated Learning mainly threaten:

a)

Storage efficiency

b)

Model integrity and convergence

c)

Feature selection

d)

Training speed only

13.

Which communication factor most affects training latency in Federated Learning?

a)

Batch size

b)

Feature dimensionality

c)

Frequency of model updates

d)

Learning rate

14.

Compared to centralized training, Federated Learning requires more:

a)

Storage

b)

Model layers

c)

Network coordination

d)

Labeled data

15.

Which technique is commonly used to reduce bandwidth usage in FL?

a)

Data augmentation

b)

Model compression

c)

Feature normalization

d)

Dropout

16.

Limited bandwidth in Federated Learning primarily results in:

a)

Higher model accuracy

b)

Faster aggregation

c)

Slower convergence

d)

Reduced model size

17.

Edge Computing improves Federated Learning mainly by:

a)

Centralizing computation

b)

Reducing latency and data transmission

c)

Increasing cloud dependency

d)

Eliminating communication

18.

Why are IoT devices challenging participants in Federated Learning?

a)

They generate less data

b)

They lack network interfaces

c)

They have limited compute and power resources

d)

They do not support ML models

19.

Which property makes Federated Learning suitable for large-scale IoT networks?

a)

Centralized storage

b)

Device-level autonomy

c)

High memory usage

d)

Offline training

20.

Which combination best represents a federated system?

a)

Cloud server + single dataset

b)

Edge devices + local training + central aggregation

c)

GPUs + shared memory

d)

IoT sensors + centralized database